{ "meta": { "source": "atlas_v13_current.html", "snapshot": "2026-10-18", "site_version": "13.2", "count": 193, "note": "Materialized view of the current audited graph; complete node fields retained. Source inspection and publication status are recorded per item. The builder performs no new empirical validation." }, "records": [ { "id": "W001", "label": "AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Code quality & security" ], "actual": [ "C:C02", "C:C05", "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C05", "C:C12" ], "printed": true, "summary": "First-adopter agent use raises commits and code volume, but complexity and warnings rise too.", "limitation": "Observational assignment; output is not delivered value.", "url": "https://arxiv.org/abs/2601.13597", "authors": "Agarwal", "year": "2026", "attributes": { "label": "AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Agarwal", "source": "https://arxiv.org/abs/2601.13597", "contribution": "First-adopter agent use raises commits and code volume, but complexity and warnings rise too.", "limitation": "Observational assignment; output is not delivered value.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_TABLES_LOCATED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass2_source_locator": "https://arxiv.org/html/2601.13597", "pass2_source_version": "arXiv v2 2026-01-27 and published DOI", "pass2_inspection_scope": "Sections 3.1--3.3 and Table 2 and design limitations", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Staggered DiD matched observables using AIDev v3", "pass2_critical_limitation": "No randomized adoption; selective repositories and adoption attribution; warning IDE-first effect not statistically significant", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C02\", \"C:C05\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Technical debt and complexity", "K:Evaluation methodology and baselines", "K:Long-running agent execution" ], "volumes": [ "V06" ] }, { "id": "W002", "label": "Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Verification & review" ], "actual": [ "C:C01", "C:C03" ], "mapped": [ "C:C01", "C:C02", "C:C03", "C:C04", "C:C08" ], "printed": true, "summary": "Delegating to an agent enables tasks beyond copilot assistance; lack of visibility constrains trust.", "limitation": "Twenty students; completion-time effects unspecified.", "url": "https://arxiv.org/abs/2507.08149", "authors": "Chen", "year": "2026", "attributes": { "label": "Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Chen", "source": "https://arxiv.org/abs/2507.08149", "contribution": "Delegating to an agent enables tasks beyond copilot assistance; lack of visibility constrains trust.", "limitation": "Twenty students; completion-time effects unspecified.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH04:ABSTRACT", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C03\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Automation bias and trust", "K:Specifications and governance", "K:Skills formation and teaching" ], "volumes": [ "V06" ] }, { "id": "W003", "label": "The Effects of Generative AI on High-Skilled Work: Evidence from Three Field Experiments with Software Developers", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Economics" ], "actual": [ "C:C01", "C:C02", "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C12" ], "printed": true, "summary": "Real-world coding assistants improve task completion, with an estimated 26% increase across thousands of developers.", "limitation": "First-generation tools; tasks completed do not measure shipped value.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Cui", "year": "2026", "attributes": { "label": "The Effects of Generative AI on High-Skilled Work: Evidence from Three Field Experiments with Software Developers", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Cui", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Real-world coding assistants improve task completion, with an estimated 26% increase across thousands of developers.", "limitation": "First-generation tools; tasks completed do not measure shipped value.", "manual_use": "Measure activity and delivery separately; require downstream outcomes.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass3_audit_primary_url": "https://pubsonline.informs.org/doi/10.1287/mnsc.2025.00535", "pass3_audit_version": "Management Science 2026; author-hosted working paper June 2025 Table 3", "pass3_audit_depth": "WORKING_PAPER_TABLE_SELECTED_PUBLISHER_ABSTRACT", "pass3_audit_methods_locators": "2025 author manuscript Table 3 and publisher abstract", "pass3_audit_sample": "Three company randomized rollout designs, 4,867 engineers", "pass3_audit_observation": "Company WIV estimates 27.38,17.94,54.03%; pooled 26.08% SE10.3", "pass3_audit_boundary": "Outcome in working Table 3 is pull requests; journal full table parity outstanding", "pass3_audit_original_data_replication": "NO", "pass3_audit_provenance": "PASS3_PRINTED_EDITION_RECONSTRUCTED_2026-10-10", "pass3_audit_date": "2026-10-10", "pass9_scope": "publisher official 15-page online supplement pp24-25,28; sample+ITT checked; no regressions refit", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C02\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Skills formation and teaching", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W004", "label": "Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Code quality & security" ], "actual": [ "C:C02", "C:C05", "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C05", "C:C12" ], "printed": true, "summary": "Early code-volume surge disappears as complexity and static-analysis findings remain elevated.", "limitation": "Matched OSS repositories cannot remove all adoption confounding.", "url": "https://arxiv.org/abs/2511.04427", "authors": "He", "year": "2026", "attributes": { "label": "Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "He", "source": "https://arxiv.org/abs/2511.04427", "contribution": "Early code-volume surge disappears as complexity and static-analysis findings remain elevated.", "limitation": "Matched OSS repositories cannot remove all adoption confounding.", "manual_use": "Measure activity and delivery separately; require downstream outcomes.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass2_source_locator": "https://www.cs.cmu.edu/~ckaestne/pdf/msr26.pdf", "pass2_source_version": "MSR 2026 publisher DOI and 19-page author PDF", "pass2_inspection_scope": "Sections 3.5 and 4.1 Table 2 printed page 7; Appendix B.3 Table 6 printed page 16", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Matched staggered DiD with three nonidentical estimators", "pass2_critical_limitation": "Estimator choices materially change quality findings; config-file use not exact agent activity; nonrandom treatment", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C02\", \"C:C05\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Technical debt and complexity", "K:Economic costs and return", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W005", "label": "Early Adoption of Agentic Coding Tools by GitHub Projects", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Verification & review" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C03", "C:C08" ], "printed": true, "summary": "Real pull-request usage is concentrated and frequently consists of just one or two agent PRs per adopting project.", "limitation": "Early adoption snapshot; does not measure organizational productivity.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Raida", "year": "2026", "attributes": { "label": "Early Adoption of Agentic Coding Tools by GitHub Projects", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Raida", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Real pull-request usage is concentrated and frequently consists of just one or two agent PRs per adopting project.", "limitation": "Early adoption snapshot; does not measure organizational productivity.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W006", "label": "Agentic Much? Adoption of Coding Agents on GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [], "mapped": [ "C:C01", "C:C02" ], "printed": true, "summary": "Coding-agent participation is spreading across public repositories and changes commit size and activity patterns.", "limitation": "Adoption and size are not effectiveness.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Robbes", "year": "2026", "attributes": { "label": "Agentic Much? Adoption of Coding Agents on GitHub", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Robbes", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Coding-agent participation is spreading across public repositories and changes commit size and activity patterns.", "limitation": "Adoption and size are not effectiveness.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption" ], "volumes": [] }, { "id": "W007", "label": "Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [], "mapped": [ "C:C01", "C:C02" ], "printed": true, "summary": "Enterprise users report perceived usefulness and practical requirements that should shape deployment.", "limitation": "IBM respondents only; perception-based.", "url": "https://arxiv.org/abs/2601.20112", "authors": "Merler", "year": "2026", "attributes": { "label": "Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Merler", "source": "https://arxiv.org/abs/2601.20112", "contribution": "Enterprise users report perceived usefulness and practical requirements that should shape deployment.", "limitation": "IBM respondents only; perception-based.", "manual_use": "Measure activity and delivery separately; require downstream outcomes.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://arxiv.org/abs/2601.20112", "pass7_identity_source_class": "author_preprint", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Automation bias and trust" ], "volumes": [] }, { "id": "W008", "label": "How Much Does AI Impact Development Speed? An Enterprise-Based Randomized Controlled Trial", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [ "C:C02" ], "mapped": [ "C:C01", "C:C02" ], "printed": true, "summary": "Controlled enterprise tasks indicate roughly 21% faster task performance with assistance.", "limitation": "Narrow tasks and 96 participants limit generalization to long-lived systems.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Paradis", "year": "2025", "attributes": { "label": "How Much Does AI Impact Development Speed? An Enterprise-Based Randomized Controlled Trial", "kind": "paper", "group": "Productivity", "year": "2025", "lead_author": "Paradis", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Controlled enterprise tasks indicate roughly 21% faster task performance with assistance.", "limitation": "Narrow tasks and 96 participants limit generalization to long-lived systems.", "manual_use": "Measure activity and delivery separately; require downstream outcomes.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2025", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C02\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W009", "label": "Productivity Assessment of Neural Code Completion", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Verification & review" ], "actual": [ "C:C02" ], "mapped": [ "C:C01", "C:C02", "C:C08" ], "printed": true, "summary": "Suggestion acceptance is only weakly associated with self-rated productivity, challenging acceptance rate as KPI.", "limitation": "Vendor users; survey not causal.", "url": "https://arxiv.org/abs/2205.06537", "authors": "Ziegler", "year": "2022", "attributes": { "label": "Productivity Assessment of Neural Code Completion", "kind": "paper", "group": "Productivity", "year": "2022", "lead_author": "Ziegler", "source": "https://arxiv.org/abs/2205.06537", "contribution": "Suggestion acceptance is only weakly associated with self-rated productivity, challenging acceptance rate as KPI.", "limitation": "Vendor users; survey not causal.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2022", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C02\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence" ], "volumes": [ "V06" ] }, { "id": "W010", "label": "Writing Code vs. Shipping Code: Productivity Effects Across Generations of AI Coding Tools", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Economics" ], "actual": [ "C:C01", "C:C02", "C:C08", "C:C11", "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C08", "C:C11", "C:C12" ], "printed": true, "summary": "Agent advances raise commits substantially more than releases; delivery throughput has lower elasticity than coding throughput.", "limitation": "GitHub activity and matched designs do not establish business value.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Demirer", "year": "2026", "attributes": { "label": "Writing Code vs. Shipping Code: Productivity Effects Across Generations of AI Coding Tools", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Demirer", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Agent advances raise commits substantially more than releases; delivery throughput has lower elasticity than coding throughput.", "limitation": "GitHub activity and matched designs do not establish business value.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no_institutional_record_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass2_source_locator": "https://www.nber.org/papers/w35275", "pass2_source_version": "NBER Working Paper 35275 September 2026 revision institutional record", "pass2_inspection_scope": "Institutional metadata and abstract; complete Sept manuscript not independently inspected", "pass2_methods_status": "PRIMARY_INSTITUTIONAL_RECORD_ONLY", "pass2_replication_status": "NO", "pass2_research_design": "Matched event study plus economic structural model as described by institution", "pass2_critical_limitation": "Observational adoption and different output endpoints; full revision and exact attribution tables not examined", "pass2_audit_date": "2026-10-10", "pass5_audit_date": "2026-10-10", "pass5_version": "NBER w35275 Sept 2026 revision; SSRN May 2026 separate abstract", "pass5_primary_locator": "https://www.nber.org/papers/w35275 ; https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6843068", "pass5_inspection_depth": "PUBLISHER_REVISION_ABSTRACT_AND_EARLIER_SSRN_ABSTRACT_ONLY", "pass5_page_scope": "Institutional abstracts only; 134-page September PDF not accessible", "pass5_sample": "September >500,000 developers; earlier May >100,000; distinct samples/estimates", "pass5_main_finding": "September cumulative commits ~30/180/240%; agent projects +80%; agent releases +30%; elasticity 0.23. May 40/140/180%; projects +50%; releases +30%; elasticity 0.25.", "pass5_residual_limitation": "No original coefficient tables or microdata inspected; estimates observational and structural, not direct firm outcomes.", "pass5_original_data_replicated": "NO", "pass5_provenance": "PASS5_2026-10-10_SCOPED_PRIMARY_AND_VERSIONED_ABSTRACT", "pass6_date": "2026-10-10", "pass6_locator": "https://www.nber.org/papers/w35275", "pass6_inspection_depth": "NBER_PRIMARY_INSTITUTIONAL_REVISED_RECORD", "pass6_page_scope": "NBER September 2026 revision abstract and author disclosures", "pass6_finding": "500k plus developer sample; 30/180/240% commit estimates; declared paid Microsoft consulting for two authors", "pass6_limitation": "SEPT_134PAGE_PDF_UNAVAILABLE", "pass6_original_data_replicated": "NO", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C02\", \"C:C08\", \"C:C11\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W011", "label": "The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Engineering structure" ], "actual": [ "C:C01", "C:C03", "C:C04", "C:C11" ], "mapped": [ "C:C01", "C:C02", "C:C03", "C:C04", "C:C07", "C:C11" ], "printed": true, "summary": "Proposes specification and verification governance to balance faster generation against reliability.", "limitation": "Synthesis rather than a new intervention trial.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Farrag", "year": "2026", "attributes": { "label": "The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Farrag", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Proposes specification and verification governance to balance faster generation against reliability.", "limitation": "Synthesis rather than a new intervention trial.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Multivocal synthesis + illustrative uncontrolled pilot", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass2_source_locator": "https://arxiv.org/html/2605.01160", "pass2_source_version": "arXiv 2605.01160 HTML primary", "pass2_inspection_scope": "Methods sections 3 and evaluation sections 7.4.1--7.4.5", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Multivocal literature review plus nonrandom illustrative before-after exercise", "pass2_critical_limitation": "Self-selected synthetic/illustrative case with no randomized control and no credible causal estimate", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C03\", \"C:C04\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Independent verification and oracles", "K:Specifications and governance", "K:Skills formation and teaching" ], "volumes": [ "V06" ] }, { "id": "W012", "label": "Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [ "C:C01", "C:C03" ], "mapped": [ "C:C01", "C:C02", "C:C03" ], "printed": true, "summary": "Millions of traces characterize tool usage, agent sessions and infrastructure optimizations.", "limitation": "Session telemetry does not establish downstream outcomes.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Liu", "year": "2026", "attributes": { "label": "Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Liu", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Millions of traces characterize tool usage, agent sessions and infrastructure optimizations.", "limitation": "Session telemetry does not establish downstream outcomes.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C03\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Long-running agent execution", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W013", "label": "Quantifying the Expectation-Realisation Gap for Agentic AI Systems", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [ "C:C03" ], "mapped": [ "C:C01", "C:C02", "C:C03" ], "printed": true, "summary": "Compares agent expectations with measured productivity and warns against extrapolating benchmark success.", "limitation": "Reinterpretation of existing measures, not new experiment.", "url": "https://arxiv.org/abs/2602.20292", "authors": "Lobentanzer", "year": "2026", "attributes": { "label": "Quantifying the Expectation-Realisation Gap for Agentic AI Systems", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Lobentanzer", "source": "https://arxiv.org/abs/2602.20292", "contribution": "Compares agent expectations with measured productivity and warns against extrapolating benchmark success.", "limitation": "Reinterpretation of existing measures, not new experiment.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2602.20292", "publication_status_note": "arXiv abstract, not full paper audited", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Benchmarks and construct validity", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W014", "label": "Adoption and Impact of Command-Line AI Coding Agents: A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C03", "C:C09" ], "printed": true, "summary": "CLI agent adoption associates with 24% more merged PRs per engineer without detectable four-month decay.", "limitation": "Merged PRs are a proxy; adopter and tenure selection remain.", "url": "https://arxiv.org/abs/2607.01418", "authors": "Murphy-Hill", "year": "2026", "attributes": { "label": "Adoption and Impact of Command-Line AI Coding Agents: A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Murphy-Hill", "source": "https://arxiv.org/abs/2607.01418", "contribution": "CLI agent adoption associates with 24% more merged PRs per engineer without detectable four-month decay.", "limitation": "Merged PRs are a proxy; adopter and tenure selection remain.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Benchmarks and construct validity", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W015", "label": "Agentic Delegation and the Language Frontier of Software Developers: A Model and Evidence from Claude Code on GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C10" ], "printed": true, "summary": "Claude Code adoption correlates with developers contributing in about 2.5 additional languages; breadth is not mastery.", "limitation": "Repository activity cannot prove actual acquired proficiency.", "url": "https://arxiv.org/abs/2605.25438", "authors": "Quispe", "year": "2026", "attributes": { "label": "Agentic Delegation and the Language Frontier of Software Developers: A Model and Evidence from Claude Code on GitHub", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Quispe", "source": "https://arxiv.org/abs/2605.25438", "contribution": "Claude Code adoption correlates with developers contributing in about 2.5 additional languages; breadth is not mastery.", "limitation": "Repository activity cannot prove actual acquired proficiency.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://arxiv.org/abs/2605.25438", "pass7_identity_source_class": "author_preprint", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Skills formation and teaching" ], "volumes": [] }, { "id": "W016", "label": "The Impact of AI Coding Assistants on Software Engineering: A Longitudinal Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Verification & review" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C08" ], "printed": true, "summary": "Most developers report less writing and greater productivity; negative experience measures also increase over time.", "limitation": "95 respondents and self-report.", "url": "https://arxiv.org/abs/2605.23135", "authors": "Vella", "year": "2026", "attributes": { "label": "The Impact of AI Coding Assistants on Software Engineering: A Longitudinal Study", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Vella", "source": "https://arxiv.org/abs/2605.23135", "contribution": "Most developers report less writing and greater productivity; negative experience measures also increase over time.", "limitation": "95 respondents and self-report.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W017", "label": "Randomized Controlled Trials for Conditional Access Optimization Agent", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [ "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C12" ], "printed": true, "summary": "Agent support improves administrative throughput and accuracy in enterprise configuration work.", "limitation": "Different domain from programming; do not present as SWE causal evidence.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Bono", "year": "2025", "attributes": { "label": "Randomized Controlled Trials for Conditional Access Optimization Agent", "kind": "paper", "group": "Productivity", "year": "2025", "lead_author": "Bono", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Agent support improves administrative throughput and accuracy in enterprise configuration work.", "limitation": "Different domain from programming; do not present as SWE causal evidence.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2025", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "Identity-administration agent RCT (not developer productivity)", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W018", "label": "Intuition to Evidence: Measuring AI's True Impact on Developer Productivity", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Verification & review" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C08" ], "printed": true, "summary": "Reports increased engineering output and shorter review cycles under AI assistance.", "limitation": "Uncontrolled before/after changes; difficult attribution.", "url": "https://arxiv.org/abs/2509.19708", "authors": "Kumar", "year": "2025", "attributes": { "label": "Intuition to Evidence: Measuring AI's True Impact on Developer Productivity", "kind": "paper", "group": "Productivity", "year": "2025", "lead_author": "Kumar", "source": "https://arxiv.org/abs/2509.19708", "contribution": "Reports increased engineering output and shorter review cycles under AI assistance.", "limitation": "Uncontrolled before/after changes; difficult attribution.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://arxiv.org/abs/2509.19708", "pass7_identity_source_class": "author_preprint", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Review capacity and maintainers", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W019", "label": "Generative AI and labour productivity: a field experiment on coding", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Economics" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C12" ], "printed": true, "summary": "Code-generation tool increases output notably for junior developers, suggesting heterogeneous gains.", "limitation": "Output-count metric; model and organization specificity.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Gambacorta", "year": "2024", "attributes": { "label": "Generative AI and labour productivity: a field experiment on coding", "kind": "paper", "group": "Productivity", "year": "2024", "lead_author": "Gambacorta", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Code-generation tool increases output notably for junior developers, suggesting heterogeneous gains.", "limitation": "Output-count metric; model and organization specificity.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2024", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass6_primary_locator": "https://www.bis.org/publications/working-paper-1208-generative-ai-and-labour-productivity-field-experiment-coding", "pass6_metadata_depth": "PRIMARY_WORKING_PAPER_AND_LATER_JOURNAL", "pass6_supporting_locator": "https://www.sciencedirect.com/science/article/pii/S1572308926000458", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W020", "label": "Measuring the Self-Reported Impact of Early-2026 AI on Technical Worker Productivity", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [ "C:C02", "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C12" ], "printed": true, "summary": "Survey respondents report major time savings with substantial heterogeneity.", "limitation": "Retrospective self estimates are not measured time saved.", "url": "https://metr.org/blog/2026-05-11-ai-usage-survey/", "authors": "Becker", "year": "2026", "attributes": { "label": "Measuring the Self-Reported Impact of Early-2026 AI on Technical Worker Productivity", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Becker", "source": "https://metr.org/blog/2026-05-11-ai-usage-survey/", "contribution": "Survey respondents report major time savings with substantial heterogeneity.", "limitation": "Retrospective self estimates are not measured time saved.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://metr.org/blog/2026-05-11-ai-usage-survey/", "publication_status_note": "METR survey, self-reported impact; not causal or timed productivity", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_REPORT", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "pass5_audit_date": "2026-10-10", "pass5_version": "METR May 11 2026 original research blog and appendix", "pass5_primary_locator": "https://metr.substack.com/p/2026-05-11-ai-usage-survey", "pass5_inspection_depth": "PRIMARY_METHODS_SURVEY_QUESTION_WORDING_FILTERING_AND_RESULTS", "pass5_page_scope": "HTML Summary, Methodology, Results, Data quality and footnotes", "pass5_sample": "359 raw unique respondents, 10 excluded anomalous -> 349 retained; convenience recruitment; approx 2% emailed response; approx 70% compensated", "pass5_main_finding": "Median self-reported value multiplier 1.4–2x and speed multiplier ~3x; retrospective 2025 1.3x, 2027 prediction 2.5x; these are beliefs and cannot be compared as experimental gains.", "pass5_residual_limitation": "No independent observation-based validation, raw respondent-level data not rerun; four listed occupational counts total 335 not the full retained 349, without proof of discrepancy.", "pass5_original_data_replicated": "NO", "pass5_provenance": "PASS5_2026-10-10_SCOPED_PRIMARY_AND_VERSIONED_ABSTRACT", "ndse2_actual_chapters_json": "[\"C:C02\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W021", "label": "The AI Engineering Report 2026: The Acceleration Whiplash", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Code quality & security" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C05", "C:C12" ], "printed": true, "summary": "Higher AI use associates with more throughput, larger PRs, more incidents and much slower review.", "limitation": "Closed vendor data; observational metrics and unreported definitions.", "url": "https://www.faros.ai/blog/ai-acceleration-whiplash-takeaways", "authors": "Faros AI", "year": "2026", "attributes": { "label": "The AI Engineering Report 2026: The Acceleration Whiplash", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Faros AI", "source": "https://www.faros.ai/blog/ai-acceleration-whiplash-takeaways", "contribution": "Higher AI use associates with more throughput, larger PRs, more incidents and much slower review.", "limitation": "Closed vendor data; observational metrics and unreported definitions.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://www.faros.ai/blog/ai-acceleration-whiplash-takeaways", "pass7_identity_source_class": "producer_primary_report", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W022", "label": "AI Coding Agents: Adoption Trends", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [], "mapped": [ "C:C01", "C:C02" ], "printed": true, "summary": "Frequent agent use has quickly become mainstream in the surveyed population.", "limitation": "Adoption levels reflect sample and do not measure value or quality.", "url": "https://blog.jetbrains.com/research/2026/08/ai-coding-agent-adoption-2026/", "authors": "JetBrains Research", "year": "2026", "attributes": { "label": "AI Coding Agents: Adoption Trends", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "JetBrains Research", "source": "https://blog.jetbrains.com/research/2026/08/ai-coding-agent-adoption-2026/", "contribution": "Frequent agent use has quickly become mainstream in the surveyed population.", "limitation": "Adoption levels reflect sample and do not measure value or quality.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://blog.jetbrains.com/research/2026/08/ai-coding-agent-adoption-2026/", "pass7_identity_source_class": "producer_primary_survey", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W023", "label": "Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [ "C:C01", "C:C02" ], "mapped": [ "C:C01", "C:C02", "C:C08" ], "printed": true, "summary": "Experienced maintainers were approximately 19% slower on familiar real-repository tasks using early-2025 tools.", "limitation": "Small sample and older tool generation; not universal effect.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Becker", "year": "2025", "attributes": { "label": "Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity", "kind": "paper", "group": "Productivity", "year": "2025", "lead_author": "Becker", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Experienced maintainers were approximately 19% slower on familiar real-repository tasks using early-2025 tools.", "limitation": "Small sample and older tool generation; not universal effect.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2025", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C02\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Review capacity and maintainers", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W024", "label": "2025 State of AI-Assisted Software Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Code quality & security" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C05", "C:C12" ], "printed": true, "summary": "AI use links with greater throughput but lower stability; existing organizational capability moderates outcomes.", "limitation": "Cross-sectional self-report; association not causal.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Google Cloud DORA", "year": "2025", "attributes": { "label": "2025 State of AI-Assisted Software Development", "kind": "paper", "group": "Productivity", "year": "2025", "lead_author": "Google Cloud DORA", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "AI use links with greater throughput but lower stability; existing organizational capability moderates outcomes.", "limitation": "Cross-sectional self-report; association not causal.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2025", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass6_primary_locator": "https://dora.dev/research/2025/dora-report/", "pass6_metadata_depth": "OFFICIAL_REPORT_INDEX", "pass6_supporting_locator": "https://dora.dev/research/2025/errata/", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Long-running agent execution" ], "volumes": [] }, { "id": "W025", "label": "Estimating AI productivity gains from Claude conversations", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Economics" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C12" ], "printed": true, "summary": "Claude conversation analysis suggests sizable theoretical time saving.", "limitation": "Counterfactual completion time is estimated by model, not observed.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Tamkin", "year": "2025", "attributes": { "label": "Estimating AI productivity gains from Claude conversations", "kind": "paper", "group": "Productivity", "year": "2025", "lead_author": "Tamkin", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "Claude conversation analysis suggests sizable theoretical time saving.", "limitation": "Counterfactual completion time is estimated by model, not observed.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass6_primary_locator": "https://www.anthropic.com/research/estimating-productivity-gains", "pass6_metadata_depth": "PRIMARY_RESEARCH_NOTE_AND_PDF", "pass6_supporting_locator": "https://assets.anthropic.com/m/28fda2ad148e2bf5/original/Estimating-AI-productivity-gains-from-Claude-conversations.pdf", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W026", "label": "Accelerate State of DevOps Report 2024", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Engineering structure" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C11" ], "printed": true, "summary": "AI uptake associated with modest delivery-throughput and stability deterioration, highlighting systems bottlenecks.", "limitation": "Correlational; differs from later DORA populations and tools.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "authors": "Google Cloud DORA", "year": "2024", "attributes": { "label": "Accelerate State of DevOps Report 2024", "kind": "paper", "group": "Productivity", "year": "2024", "lead_author": "Google Cloud DORA", "source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "contribution": "AI uptake associated with modest delivery-throughput and stability deterioration, highlighting systems bottlenecks.", "limitation": "Correlational; differs from later DORA populations and tools.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2024", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass6_primary_locator": "https://dora.dev/research/2024/dora-report/", "pass6_metadata_depth": "OFFICIAL_REPORT_INDEX", "pass6_supporting_locator": "https://dora.dev/research/2024/errata/", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Long-running agent execution" ], "volumes": [] }, { "id": "W027", "label": "Beyond the Copilot: Scaling the Agentic Product Development Life Cycle", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity" ], "actual": [], "mapped": [ "C:C01", "C:C02", "C:C11" ], "printed": true, "summary": "Some organizations accelerate while a substantial subset reports declining productivity.", "limitation": "Self-reported by leaders; selection and measurement limitations.", "url": "https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/beyond-the-copilot-scaling-the-agentic-product-development-life-cycle", "authors": "Relyea", "year": "2026", "attributes": { "label": "Beyond the Copilot: Scaling the Agentic Product Development Life Cycle", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Relyea", "source": "https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/beyond-the-copilot-scaling-the-agentic-product-development-life-cycle", "contribution": "Some organizations accelerate while a substantial subset reports declining productivity.", "limitation": "Self-reported by leaders; selection and measurement limitations.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/beyond-the-copilot-scaling-the-agentic-product-development-life-cycle", "pass7_identity_source_class": "producer_primary_report", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-productivity", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W028", "label": "The AI Revolution in Software Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Productivity", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C07", "C:C11", "C:C12" ], "printed": true, "summary": "Advocates transforming the development lifecycle rather than optimizing code generation alone.", "limitation": "Extrapolated and survey-based benefits are not verified causal estimates.", "url": "https://www.mckinsey.com/~/media/mckinsey/business%20functions/tech%20and%20ai/our%20insights/the%20ai%20revolution%20in%20software%20development/the-ai-revolution-in-software-development_final.pdf", "authors": "Relyea", "year": "2026", "attributes": { "label": "The AI Revolution in Software Development", "kind": "paper", "group": "Productivity", "year": "2026", "lead_author": "Relyea", "source": "https://www.mckinsey.com/~/media/mckinsey/business%20functions/tech%20and%20ai/our%20insights/the%20ai%20revolution%20in%20software%20development/the-ai-revolution-in-software-development_final.pdf", "contribution": "Advocates transforming the development lifecycle rather than optimizing code generation alone.", "limitation": "Extrapolated and survey-based benefits are not verified causal estimates.", "manual_use": "Measure activity and delivery separately; require downstream outcomes.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://www.mckinsey.com/~/media/mckinsey/business%20functions/tech%20and%20ai/our%20insights/the%20ai%20revolution%20in%20software%20development/the-ai-revolution-in-software-development_final.pdf", "publication_status_note": "Industry commentary, not a randomized coding experiment", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_REPORT", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass5_audit_date": "2026-10-10", "pass5_version": "McKinsey Tech & AI Practice April 2026 book excerpt (nine-page original PDF)", "pass5_primary_locator": "https://www.mckinsey.com/~/media/mckinsey/business%20functions/tech%20and%20ai/our%20insights/the%20ai%20revolution%20in%20software%20development/the-ai-revolution-in-software-development_final.pdf", "pass5_inspection_depth": "PRIMARY_FULL_NINE_PAGE_PDF_SELECT_METRIC_CONTEXT", "pass5_page_scope": "PDF pp.1-4, esp. pp.2-4 (vignette, exhibit, organizational analysis)", "pass5_sample": "Anonymized bank vignette; illustrative four-level leverage exhibit; analysis of nearly 300 public companies cited from separate 2025 work", "pass5_main_finding": "20x figure describes next-frontier potential; text describes Level 4 as largely experimental; top-quintile 16–30% and 31–45% claim comes from separately cited cross-company material, not the same 20x trial.", "pass5_residual_limitation": "No linked raw implementation metrics, confidence intervals or independent observational validation in this nine-page excerpt; must not call 20x a measured population mean.", "pass5_original_data_replicated": "NO", "pass5_provenance": "PASS5_2026-10-10_SCOPED_PRIMARY_AND_VERSIONED_ABSTRACT", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Independent verification and oracles", "K:Architecture and modularity" ], "volumes": [ "V06" ] }, { "id": "W029", "label": "Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [ "C:C05" ], "mapped": [ "C:C05", "C:C06", "C:C08" ], "printed": true, "summary": "Merged agent PRs still introduce code smells and bugs; size of change dominates agent-specific differences.", "limitation": "Static-analysis findings are not confirmed operational incidents.", "url": "https://arxiv.org/abs/2601.20109", "authors": "Cynthia", "year": "2026", "attributes": { "label": "Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Cynthia", "source": "https://arxiv.org/abs/2601.20109", "contribution": "Merged agent PRs still introduce code smells and bugs; size of change dominates agent-specific differences.", "limitation": "Static-analysis findings are not confirmed operational incidents.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Technical debt and complexity" ], "volumes": [ "V06" ] }, { "id": "W030", "label": "Workspace Topology as an Attack Vector in Agentic Coding Assistants", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Engineering structure" ], "actual": [ "C:C06" ], "mapped": [ "C:C05", "C:C06", "C:C11" ], "printed": true, "summary": "Modular workspace layouts reduce indirect injection success, indicating architecture can be a security control.", "limitation": "Only open-weight agents; no transfer figures in bibliography.", "url": "https://arxiv.org/abs/2608.14876", "authors": "Day", "year": "2026", "attributes": { "label": "Workspace Topology as an Attack Vector in Agentic Coding Assistants", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Day", "source": "https://arxiv.org/abs/2608.14876", "contribution": "Modular workspace layouts reduce indirect injection success, indicating architecture can be a security control.", "limitation": "Only open-weight agents; no transfer figures in bibliography.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Vulnerability and secure code", "K:Prompt injection and malicious tools", "K:Architecture and modularity", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W031", "label": "More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [ "C:C05" ], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C08" ], "printed": true, "summary": "AI-generated changes miss existing reuse opportunities, creating unnecessary new code.", "limitation": "Numerical effects and sentiment findings not supplied in bibliography.", "url": "https://arxiv.org/abs/2601.21276", "authors": "Huang", "year": "2026", "attributes": { "label": "More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Huang", "source": "https://arxiv.org/abs/2601.21276", "contribution": "AI-generated changes miss existing reuse opportunities, creating unnecessary new code.", "limitation": "Numerical effects and sentiment findings not supplied in bibliography.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Missing outcome details", "editorial_priority": "VERIFY", "bibliography_year": "2026", "original_evidence_class": "Missing outcome details", "reviewed_evidence_class": "Missing outcome details", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Agent failure and escalation", "K:Code reuse and duplication" ], "volumes": [ "V06" ] }, { "id": "W032", "label": "Understanding the Impact of AI Code Assistants on Security API Usage", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [], "mapped": [ "C:C05", "C:C06", "C:C07", "C:C08" ], "printed": true, "summary": "Copilot improves functional correctness without reliably improving secure API use or developer risk recognition.", "limitation": "Forty-four participants and selected security APIs.", "url": "https://arxiv.org/abs/2607.11348", "authors": "Mousavi", "year": "2026", "attributes": { "label": "Understanding the Impact of AI Code Assistants on Security API Usage", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Mousavi", "source": "https://arxiv.org/abs/2607.11348", "contribution": "Copilot improves functional correctness without reliably improving secure API use or developer risk recognition.", "limitation": "Forty-four participants and selected security APIs.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Independent verification and oracles", "K:Vulnerability and secure code", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W033", "label": "How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [], "mapped": [ "C:C02", "C:C05", "C:C06", "C:C08" ], "printed": true, "summary": "Agent pull requests contain more commits and different change structures than human PRs.", "limitation": "Structural contrasts are not defect-rate comparisons; shares AIDev cohort.", "url": "https://arxiv.org/abs/2601.17581", "authors": "Ogenrwot", "year": "2026", "attributes": { "label": "How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Ogenrwot", "source": "https://arxiv.org/abs/2601.17581", "contribution": "Agent pull requests contain more commits and different change structures than human PRs.", "limitation": "Structural contrasts are not defect-rate comparisons; shares AIDev cohort.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_LOCATED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Architecture and modularity", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W034", "label": "Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:What agents can do" ], "actual": [ "C:C03", "C:C05" ], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "PR acceptance depends markedly on task category; measured agent differences are less robust.", "limitation": "Acceptance reflects maintainer decisions rather than true quality; shared AIDev data.", "url": "https://arxiv.org/abs/2602.08915", "authors": "Pinna", "year": "2026", "attributes": { "label": "Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Pinna", "source": "https://arxiv.org/abs/2602.08915", "contribution": "PR acceptance depends markedly on task category; measured agent differences are less robust.", "limitation": "Acceptance reflects maintainer decisions rather than true quality; shared AIDev data.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH05:FULL_TEXT_OPENED_METHODS_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W035", "label": "Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [], "mapped": [ "C:C05", "C:C06", "C:C08" ], "printed": true, "summary": "Agent security contributions emphasize hardening, face long reviews, and are affected by PR complexity.", "limitation": "Hardening versus vulnerability fixing must be kept separate; shared AIDev data.", "url": "https://arxiv.org/abs/2601.00477", "authors": "Siddiq", "year": "2026", "attributes": { "label": "Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Siddiq", "source": "https://arxiv.org/abs/2601.00477", "contribution": "Agent security contributions emphasize hardening, face long reviews, and are affected by PR complexity.", "limitation": "Hardening versus vulnerability fixing must be kept separate; shared AIDev data.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Technical debt and complexity", "K:Vulnerability and secure code", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W036", "label": "On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [ "C:C05" ], "mapped": [ "C:C05", "C:C06", "C:C08" ], "printed": true, "summary": "Most Claude Code PRs merge, but nearly half of merged changes undergo human revision.", "limitation": "Small initial adoption cohort; merge rate is not field reliability.", "url": "https://arxiv.org/abs/2509.14745", "authors": "Watanabe", "year": "2026", "attributes": { "label": "On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Watanabe", "source": "https://arxiv.org/abs/2509.14745", "contribution": "Most Claude Code PRs merge, but nearly half of merged changes undergo human revision.", "limitation": "Small initial adoption cohort; merge rate is not field reliability.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED; CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W037", "label": "After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C03", "C:C04", "C:C05", "C:C06" ], "printed": true, "summary": "Agent add-on scanners disagree widely and can miss malicious or unsafe skills.", "limitation": "Security of extensions is not security of generated code.", "url": "https://arxiv.org/abs/2609.17274", "authors": "Xiong", "year": "2026", "attributes": { "label": "After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Xiong", "source": "https://arxiv.org/abs/2609.17274", "contribution": "Agent add-on scanners disagree widely and can miss malicious or unsafe skills.", "limitation": "Security of extensions is not security of generated code.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Agent failure and escalation", "K:Vulnerability and secure code", "K:Prompt injection and malicious tools", "K:Dependencies and agent supply chain", "K:Specifications and governance", "K:Skills formation and teaching" ], "volumes": [] }, { "id": "W038", "label": "Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C06", "C:C07" ], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C07" ], "printed": true, "summary": "External, localized security feedback improves model vulnerability remediation more consistently than self-explanation.", "limitation": "Controlled benchmarks, residual risk and model sensitivity remain.", "url": "https://arxiv.org/abs/2506.23034", "authors": "Yan", "year": "2026", "attributes": { "label": "Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Yan", "source": "https://arxiv.org/abs/2506.23034", "contribution": "External, localized security feedback improves model vulnerability remediation more consistently than self-explanation.", "limitation": "Controlled benchmarks, residual risk and model sensitivity remain.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:PDF_PAGE_RELEVANT; CH07:FULLTEXT_HTML", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\", \"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Vulnerability and secure code", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W039", "label": "Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C05" ], "mapped": [ "C:C05", "C:C06", "C:C09" ], "printed": true, "summary": "AI and human code exhibit different fault types: AI more unused constructs and severe vulnerabilities; humans more structural complexity.", "limitation": "Authorship and sampling matter; not a universal quality hierarchy.", "url": "https://arxiv.org/abs/2508.21634", "authors": "Cotroneo", "year": "2025", "attributes": { "label": "Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Cotroneo", "source": "https://arxiv.org/abs/2508.21634", "contribution": "AI and human code exhibit different fault types: AI more unused constructs and severe vulnerabilities; humans more structural complexity.", "limitation": "Authorship and sampling matter; not a universal quality hierarchy.", "manual_use": "Convert the reported risk into a static, behavioral or security acceptance gate.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Technical debt and complexity", "K:Vulnerability and secure code", "K:Architecture and modularity", "K:Ownership and knowledge transfer", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W040", "label": "Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C05", "C:C06" ], "printed": true, "summary": "Around a quarter to a third of selected AI-attributed snippets trigger security weaknesses; static warnings support partial remediation.", "limitation": "No comparable human-authored control.", "url": "https://arxiv.org/abs/2310.02059", "authors": "Fu", "year": "2025", "attributes": { "label": "Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Fu", "source": "https://arxiv.org/abs/2310.02059", "contribution": "Around a quarter to a third of selected AI-attributed snippets trigger security weaknesses; static warnings support partial remediation.", "limitation": "No comparable human-authored control.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Vulnerability and secure code", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W041", "label": "Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C06" ], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "Most selected files have no mapped vulnerability, while thousands of CWE instances remain and rates vary by language.", "limitation": "No matched human baseline and marker-based selection.", "url": "https://arxiv.org/abs/2510.26103", "authors": "Schreiber", "year": "2025", "attributes": { "label": "Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Schreiber", "source": "https://arxiv.org/abs/2510.26103", "contribution": "Most selected files have no mapped vulnerability, while thousands of CWE instances remain and rates vary by language.", "limitation": "No matched human baseline and marker-based selection.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2025", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:PDF_PAGE_RELEVANT", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Vulnerability and secure code", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W042", "label": "Security Degradation in Iterative AI Code Generation: A Systematic Analysis of the Paradox", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:What agents can do" ], "actual": [], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C12" ], "printed": true, "summary": "Iteration intended to improve code can accumulate critical security vulnerabilities if no external gate interrupts it.", "limitation": "Ten crafted starting programs; ecological validity limited.", "url": "https://arxiv.org/abs/2506.11022", "authors": "Shukla", "year": "2025", "attributes": { "label": "Security Degradation in Iterative AI Code Generation: A Systematic Analysis of the Paradox", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Shukla", "source": "https://arxiv.org/abs/2506.11022", "contribution": "Iteration intended to improve code can accumulate critical security vulnerabilities if no external gate interrupts it.", "limitation": "Ten crafted starting programs; ecological validity limited.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Vulnerability and secure code", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W043", "label": "We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C06" ], "mapped": [ "C:C03", "C:C04", "C:C05", "C:C06" ], "printed": true, "summary": "Nonexistent package names create supply-chain takeover possibilities, requiring registry existence and dependency-policy gates.", "limitation": "Model generation and repository dependency adoption are different endpoints.", "url": "https://arxiv.org/abs/2406.10279", "authors": "Spracklen", "year": "2025", "attributes": { "label": "We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Spracklen", "source": "https://arxiv.org/abs/2406.10279", "contribution": "Nonexistent package names create supply-chain takeover possibilities, requiring registry existence and dependency-policy gates.", "limitation": "Model generation and repository dependency adoption are different endpoints.", "manual_use": "Convert the reported risk into a static, behavioral or security acceptance gate.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:PDF_PAGE_RELEVANT", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Benchmarks and construct validity", "K:Dependencies and agent supply chain", "K:Specifications and governance", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W044", "label": "An Empirical Study of Code Clones from Commercial AI Code Generators", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C05" ], "mapped": [ "C:C02", "C:C05", "C:C06" ], "printed": true, "summary": "Some generated fragments replicate code almost exactly, raising reuse, maintenance and provenance concerns.", "limitation": "Generator outputs measured; longitudinal repository clone prevalence unknown.", "url": "https://doi.org/10.1145/3729397", "authors": "Wu", "year": "2025", "attributes": { "label": "An Empirical Study of Code Clones from Commercial AI Code Generators", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Wu", "source": "https://doi.org/10.1145/3729397", "contribution": "Some generated fragments replicate code almost exactly, raising reuse, maintenance and provenance concerns.", "limitation": "Generator outputs measured; longitudinal repository clone prevalence unknown.", "manual_use": "Convert the reported risk into a static, behavioral or security acceptance gate.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://doi.org/10.1145/3729397", "publication_status_note": "ACM FSE published paper; full manuscript not audited", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PUBLISHER_DOI_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1145/3729397", "previous_chapter_audit_registers": "CH05:PUBLISHER_FULL_HTML_LOCATED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Code reuse and duplication", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W045", "label": "Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:What agents can do" ], "actual": [ "C:C06", "C:C07" ], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C07" ], "printed": true, "summary": "Agents succeed functionally much more often than they satisfy security criteria, making correctness and security separate gates.", "limitation": "Benchmark selected vulnerability-inducing feature requests.", "url": "https://arxiv.org/abs/2512.03262", "authors": "Zhao", "year": "2025", "attributes": { "label": "Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Zhao", "source": "https://arxiv.org/abs/2512.03262", "contribution": "Agents succeed functionally much more often than they satisfy security criteria, making correctness and security separate gates.", "limitation": "Benchmark selected vulnerability-inducing feature requests.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:PDF_PAGE_RELEVANT; CH07:FULLTEXT_HTML", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\", \"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Vulnerability and secure code" ], "volumes": [ "V06" ] }, { "id": "W046", "label": "Do Users Write More Insecure Code with AI Assistants?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Verification & review" ], "actual": [ "C:C06" ], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C08" ], "printed": true, "summary": "On several security tasks the 2022-era assistant lowers the share of secure submissions while increasing confidence.", "limitation": "Small predominantly student sample; old Codex model.", "url": "https://arxiv.org/abs/2211.03622", "authors": "Perry", "year": "2023", "attributes": { "label": "Do Users Write More Insecure Code with AI Assistants?", "kind": "paper", "group": "Code quality & security", "year": "2023", "lead_author": "Perry", "source": "https://arxiv.org/abs/2211.03622", "contribution": "On several security tasks the 2022-era assistant lowers the share of secure submissions while increasing confidence.", "limitation": "Small predominantly student sample; old Codex model.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2023", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:PDF_PAGE_RELEVANT", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Automation bias and trust", "K:Agent failure and escalation", "K:Vulnerability and secure code", "K:Skills formation and teaching", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W047", "label": "Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C05", "C:C06" ], "printed": true, "summary": "Assisted and control groups exhibit similar security-critical bug rates for one C linked-list implementation.", "limitation": "One low-level task; cannot generalize or negate other studies.", "url": "https://arxiv.org/abs/2208.09727", "authors": "Sandoval", "year": "2023", "attributes": { "label": "Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants", "kind": "paper", "group": "Code quality & security", "year": "2023", "lead_author": "Sandoval", "source": "https://arxiv.org/abs/2208.09727", "contribution": "Assisted and control groups exhibit similar security-critical bug rates for one C linked-list implementation.", "limitation": "One low-level task; cannot generalize or negate other studies.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2023", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Vulnerability and secure code", "K:Skills formation and teaching", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W048", "label": "Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "Copilot generates vulnerable implementations in deliberately security-sensitive prompts, motivating deterministic security checks.", "limitation": "Curated weak scenarios; 2021 model and no realistic prevalence estimate.", "url": "https://arxiv.org/abs/2108.09293", "authors": "Pearce", "year": "2022", "attributes": { "label": "Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions", "kind": "paper", "group": "Code quality & security", "year": "2022", "lead_author": "Pearce", "source": "https://arxiv.org/abs/2108.09293", "contribution": "Copilot generates vulnerable implementations in deliberately security-sensitive prompts, motivating deterministic security checks.", "limitation": "Curated weak scenarios; 2021 model and no realistic prevalence estimate.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2022", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Benchmarks and construct validity", "K:Vulnerability and secure code" ], "volumes": [] }, { "id": "W049", "label": "The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "Modern frontier models hallucinate fewer packages, but shared plausible unregistered names remain exploitable.", "limitation": "Package frequency is a model-and-task dependent measurement.", "url": "https://arxiv.org/abs/2605.17062", "authors": "Churilov", "year": "2026", "attributes": { "label": "The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Churilov", "source": "https://arxiv.org/abs/2605.17062", "contribution": "Modern frontier models hallucinate fewer packages, but shared plausible unregistered names remain exploitable.", "limitation": "Package frequency is a model-and-task dependent measurement.", "manual_use": "Convert the reported risk into a static, behavioral or security acceptance gate.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Dependencies and agent supply chain", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W050", "label": "Understanding the (In)Security of Vibe-Coded Applications", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C05", "C:C06" ], "printed": true, "summary": "Most audited apps had detectable vulnerabilities; basic prompting only partially prevents replayed mistakes.", "limitation": "Selective sampling; not representative prevalence of all AI-created apps.", "url": "https://arxiv.org/abs/2606.23130", "authors": "Deng", "year": "2026", "attributes": { "label": "Understanding the (In)Security of Vibe-Coded Applications", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Deng", "source": "https://arxiv.org/abs/2606.23130", "contribution": "Most audited apps had detectable vulnerabilities; basic prompting only partially prevents replayed mistakes.", "limitation": "Selective sampling; not representative prevalence of all AI-created apps.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Vulnerability and secure code", "K:System understanding and rationale" ], "volumes": [] }, { "id": "W051", "label": "From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C02", "C:C05", "C:C06", "C:C09" ], "printed": true, "summary": "No broad degradation on observed quality signals, but developers anticipate worse maintainability of others' AI output.", "limitation": "Perceived maintainability is not measured effort; sampling differs from negative studies.", "url": "https://arxiv.org/abs/2607.05677", "authors": "Fang", "year": "2026", "attributes": { "label": "From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Fang", "source": "https://arxiv.org/abs/2607.05677", "contribution": "No broad degradation on observed quality signals, but developers anticipate worse maintainability of others' AI output.", "limitation": "Perceived maintainability is not measured effort; sampling differs from negative studies.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Automation bias and trust", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W052", "label": "What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C05" ], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "Generated functions are shorter but security effects vary across Python Java and C; normalize size before judging complexity.", "limitation": "Preprint; function-level comparisons not entire codebases.", "url": "https://arxiv.org/abs/2609.12708", "authors": "Improta", "year": "2026", "attributes": { "label": "What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Improta", "source": "https://arxiv.org/abs/2609.12708", "contribution": "Generated functions are shorter but security effects vary across Python Java and C; normalize size before judging complexity.", "limitation": "Preprint; function-level comparisons not entire codebases.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Technical debt and complexity", "K:Vulnerability and secure code", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W053", "label": "Scanning the Harness: Configuration Exposures in AI Coding-Agent Supply Chains", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Engineering structure" ], "actual": [ "C:C06" ], "mapped": [ "C:C05", "C:C06", "C:C11" ], "printed": true, "summary": "Exposed execution grants, versionless MCP servers, and overbroad skill approvals make harness configuration an attack surface.", "limitation": "Static configuration exposure does not prove exploitation.", "url": "https://arxiv.org/abs/2609.07360", "authors": "Kapner", "year": "2026", "attributes": { "label": "Scanning the Harness: Configuration Exposures in AI Coding-Agent Supply Chains", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Kapner", "source": "https://arxiv.org/abs/2609.07360", "contribution": "Exposed execution grants, versionless MCP servers, and overbroad skill approvals make harness configuration an attack surface.", "limitation": "Static configuration exposure does not prove exploitation.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:PDF_PAGE_RELEVANT", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Prompt injection and malicious tools", "K:Dependencies and agent supply chain", "K:Skills formation and teaching" ], "volumes": [ "V06" ] }, { "id": "W054", "label": "Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C02", "C:C05" ], "mapped": [ "C:C02", "C:C05", "C:C06" ], "printed": true, "summary": "Post-merge revert behavior varies across named agents; aggregate agent-vs-human averages hide this heterogeneity.", "limitation": "Reverts inferred from messages and security smells from regex.", "url": "https://arxiv.org/abs/2609.17598", "authors": "Kraishan", "year": "2026", "attributes": { "label": "Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Kraishan", "source": "https://arxiv.org/abs/2609.17598", "contribution": "Post-merge revert behavior varies across named agents; aggregate agent-vs-human averages hide this heterogeneity.", "limitation": "Reverts inferred from messages and security smells from regex.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:TARGETED_FULL_TEXT_PAGES_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C02\", \"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Vulnerability and secure code", "K:Evaluation methodology and baselines", "K:Long-running agent execution", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W055", "label": "Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [ "C:C05" ], "mapped": [ "C:C02", "C:C05", "C:C06" ], "printed": true, "summary": "Many assistant-authored commits introduce code smells, and some findings survive subsequent maintenance.", "limitation": "No comparable human commit baseline; smells not confirmed defects.", "url": "https://arxiv.org/abs/2603.28592", "authors": "Liu", "year": "2026", "attributes": { "label": "Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Liu", "source": "https://arxiv.org/abs/2603.28592", "contribution": "Many assistant-authored commits introduce code smells, and some findings survive subsequent maintenance.", "limitation": "No comparable human commit baseline; smells not confirmed defects.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Technical debt and complexity", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W056", "label": "A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "AI code has fewer CodeQL alerts and cross-file duplicates in selected units, yet is edited more after introduction.", "limitation": "Selection, granularity and matching differ from repository-level debt studies.", "url": "https://arxiv.org/abs/2603.27130", "authors": "Mao", "year": "2026", "attributes": { "label": "A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Mao", "source": "https://arxiv.org/abs/2603.27130", "contribution": "AI code has fewer CodeQL alerts and cross-file duplicates in selected units, yet is edited more after introduction.", "limitation": "Selection, granularity and matching differ from repository-level debt studies.", "manual_use": "Use to design independent static-analysis and repair gates; verify residual vulnerability, not just suggested fixes.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Code reuse and duplication", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W057", "label": "How Do AI Coding Agents Contribute to Software Development? An Empirical Study of Agentic Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Productivity" ], "actual": [ "C:C05" ], "mapped": [ "C:C02", "C:C05", "C:C06" ], "printed": true, "summary": "Proposes to compare agent contribution and merge patterns over adoption lifecycle with human PR baselines.", "limitation": "Bibliography explicitly lacks recorded results: no outcome claim warranted.", "url": "https://arxiv.org/abs/2607.21832", "authors": "Mazloomzadeh", "year": "2026", "attributes": { "label": "How Do AI Coding Agents Contribute to Software Development? An Empirical Study of Agentic Pull Requests", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Mazloomzadeh", "source": "https://arxiv.org/abs/2607.21832", "contribution": "Proposes to compare agent contribution and merge patterns over adoption lifecycle with human PR baselines.", "limitation": "Bibliography explicitly lacks recorded results: no outcome claim warranted.", "manual_use": "Include in the research inventory but do not cite as support for a measured outcome until the primary results are checked.", "evidence_class": "Missing outcome details", "editorial_priority": "VERIFY", "bibliography_year": "2026", "original_evidence_class": "Missing outcome details", "reviewed_evidence_class": "Missing outcome details", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Architecture and modularity", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W058", "label": "Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent Adoption in OSS", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:System knowledge & memory" ], "actual": [ "C:C05", "C:C11" ], "mapped": [ "C:C05", "C:C06", "C:C09", "C:C10", "C:C11" ], "printed": true, "summary": "Agent adoption correlates with higher code complexity but does not significantly reduce newcomer participation or retention.", "limitation": "No actual onboarding time or knowledge measurement.", "url": "https://arxiv.org/abs/2607.01810", "authors": "Xu", "year": "2026", "attributes": { "label": "Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent Adoption in OSS", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Xu", "source": "https://arxiv.org/abs/2607.01810", "contribution": "Agent adoption correlates with higher code complexity but does not significantly reduce newcomer participation or retention.", "limitation": "No actual onboarding time or knowledge measurement.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Technical debt and complexity", "K:Onboarding and developer fluency", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W059", "label": "AI-Generated Smells: An Analysis of Code and Architecture in LLM- and Agent-Driven Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:Engineering structure" ], "actual": [ "C:C05" ], "mapped": [ "C:C02", "C:C05", "C:C06", "C:C11" ], "printed": true, "summary": "Larger generated outputs are associated with coupling and architectural smells even when tests pass.", "limitation": "Small smell counts; correlation with LOC not a causal law.", "url": "https://arxiv.org/abs/2605.02741", "authors": "Zhu", "year": "2026", "attributes": { "label": "AI-Generated Smells: An Analysis of Code and Architecture in LLM- and Agent-Driven Development", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Zhu", "source": "https://arxiv.org/abs/2605.02741", "contribution": "Larger generated outputs are associated with coupling and architectural smells even when tests pass.", "limitation": "Small smell counts; correlation with LOC not a causal law.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:NOT_FULL_TEXT_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Technical debt and complexity", "K:Architecture and modularity" ], "volumes": [ "V06" ] }, { "id": "W060", "label": "Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security", "T:What agents can do" ], "actual": [ "C:C03", "C:C06" ], "mapped": [ "C:C03", "C:C05", "C:C06" ], "printed": true, "summary": "Workspace and retrieved-content injections can induce agents to execute unwanted commands.", "limitation": "Attack configurations are adversarial, not real-world incidence rates.", "url": "https://arxiv.org/abs/2509.22040", "authors": "Liu", "year": "2025", "attributes": { "label": "Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Liu", "source": "https://arxiv.org/abs/2509.22040", "contribution": "Workspace and retrieved-content injections can induce agents to execute unwanted commands.", "limitation": "Attack configurations are adversarial, not real-world incidence rates.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:ARXIV_ABSTRACT_VERIFIED; CH06:PRIMARY_ABSTRACT_ONLY", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C06\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Prompt injection and malicious tools" ], "volumes": [ "V06" ] }, { "id": "W061", "label": "2025 GenAI Code Security Report", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C07" ], "printed": true, "summary": "Functional model progress does not automatically translate into fewer code security-test failures.", "limitation": "Vendor-created prompts and benchmarks; not peer reviewed.", "url": "https://www.veracode.com/wp-content/uploads/2025_GenAI_Code_Security_Report_Final.pdf", "authors": "Veracode", "year": "2025", "attributes": { "label": "2025 GenAI Code Security Report", "kind": "paper", "group": "Code quality & security", "year": "2025", "lead_author": "Veracode", "source": "https://www.veracode.com/wp-content/uploads/2025_GenAI_Code_Security_Report_Final.pdf", "contribution": "Functional model progress does not automatically translate into fewer code security-test failures.", "limitation": "Vendor-created prompts and benchmarks; not peer reviewed.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2025", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://www.veracode.com/wp-content/uploads/2025_GenAI_Code_Security_Report_Final.pdf", "pass7_identity_source_class": "original_report_pdf", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-code-quality-security", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Agent failure and escalation", "K:Vulnerability and secure code" ], "volumes": [] }, { "id": "W062", "label": "Vibe Security Radar", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Code quality & security" ], "actual": [], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C07" ], "printed": true, "summary": "Public vulnerability disclosures with coding-agent provenance show verifiable safety failures in the field.", "limitation": "Source marker coverage is incomplete; denominator not interpretable as risk rate.", "url": "https://github.com/HQ1995/vibe-security-radar", "authors": "Zhao", "year": "2026", "attributes": { "label": "Vibe Security Radar", "kind": "paper", "group": "Code quality & security", "year": "2026", "lead_author": "Zhao", "source": "https://github.com/HQ1995/vibe-security-radar", "contribution": "Public vulnerability disclosures with coding-agent provenance show verifiable safety failures in the field.", "limitation": "Source marker coverage is incomplete; denominator not interpretable as risk rate.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://github.com/HQ1995/vibe-security-radar", "pass7_identity_source_class": "author_software_repository", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-code-quality-security", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Agent failure and escalation", "K:Vulnerability and secure code", "K:Specifications and governance" ], "volumes": [] }, { "id": "W063", "label": "An Endless Stream of AI Slop: How Developers Discuss the Burden of AI-Assisted Software Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Code quality & security" ], "actual": [ "C:C08" ], "mapped": [ "C:C05", "C:C07", "C:C08", "C:C11", "C:C12" ], "printed": true, "summary": "Open-source contributors describe reviewer overload and quality externalities when code generation becomes cheaper than review.", "limitation": "Public forum perceptions are not verified costs or defect counts.", "url": "https://arxiv.org/abs/2603.27249", "authors": "Baltes", "year": "2026", "attributes": { "label": "An Endless Stream of AI Slop: How Developers Discuss the Burden of AI-Assisted Software Development", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Baltes", "source": "https://arxiv.org/abs/2603.27249", "contribution": "Open-source contributors describe reviewer overload and quality externalities when code generation becomes cheaper than review.", "limitation": "Public forum perceptions are not verified costs or defect counts.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Economic costs and return" ], "volumes": [ "V06" ] }, { "id": "W064", "label": "Studying Quality Improvements Recommended via Manual and Automated Code Review", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "AI comments cover only a small share of human findings and generate much additional low-value review text.", "limitation": "One model generation and selected PRs.", "url": "https://arxiv.org/abs/2602.11925", "authors": "Crupi", "year": "2026", "attributes": { "label": "Studying Quality Improvements Recommended via Manual and Automated Code Review", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Crupi", "source": "https://arxiv.org/abs/2602.11925", "contribution": "AI comments cover only a small share of human findings and generate much additional low-value review text.", "limitation": "One model generation and selected PRs.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers" ], "volumes": [ "V06" ] }, { "id": "W065", "label": "These Aren't the Reviews You're Looking For: How Humans Review AI-Generated Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Most agent PRs have no recorded human review, but same-repository human PRs also often lack review.", "limitation": "Recorded GitHub review is not total review rigor; shared AIDev data.", "url": "https://arxiv.org/abs/2605.02273", "authors": "Duma", "year": "2026", "attributes": { "label": "These Aren't the Reviews You're Looking For: How Humans Review AI-Generated Pull Requests", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Duma", "source": "https://arxiv.org/abs/2605.02273", "contribution": "Most agent PRs have no recorded human review, but same-repository human PRs also often lack review.", "limitation": "Recorded GitHub review is not total review rigor; shared AIDev data.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W066", "label": "Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Explanations alter review trust and perceived usefulness; trust must be distinguished from objective agreement.", "limitation": "Small participant pool and proxy trust metrics.", "url": "https://arxiv.org/abs/2607.24601", "authors": "Gao", "year": "2026", "attributes": { "label": "Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Gao", "source": "https://arxiv.org/abs/2607.24601", "contribution": "Explanations alter review trust and perceived usefulness; trust must be distinguished from objective agreement.", "limitation": "Small participant pool and proxy trust metrics.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://arxiv.org/abs/2607.24601", "pass7_identity_source_class": "author_preprint", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Automation bias and trust", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W067", "label": "(Don't) Trust, but (Don't) Verify: Developers' Attention to Security in AI-Generated Code", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Code quality & security" ], "actual": [ "C:C10" ], "mapped": [ "C:C05", "C:C06", "C:C07", "C:C08", "C:C10" ], "printed": true, "summary": "Users select unsafe suggestions nearly as often as safe ones; editing correlates with fewer vulnerabilities.", "limitation": "Four selected C tasks; 2027 conference claim relies on current preprint.", "url": "https://arxiv.org/abs/2609.21020", "authors": "Khalid", "year": "2026", "attributes": { "label": "(Don't) Trust, but (Don't) Verify: Developers' Attention to Security in AI-Generated Code", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Khalid", "source": "https://arxiv.org/abs/2609.21020", "contribution": "Users select unsafe suggestions nearly as often as safe ones; editing correlates with fewer vulnerabilities.", "limitation": "Four selected C tasks; 2027 conference claim relies on current preprint.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust", "K:Independent verification and oracles", "K:Vulnerability and secure code" ], "volumes": [ "V06" ] }, { "id": "W068", "label": "Behind Agentic Pull Requests: An Empirical Study on Developer Interventions in AI Agent-Authored Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C07" ], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Human interventions occur on fewer agent PRs, but those interventions are often more extensive and guidance-oriented.", "limitation": "Metadata events cannot certify actual review quality; shared AIDev data.", "url": "https://espace2.etsmtl.ca/id/eprint/34495/", "authors": "Khelifi", "year": "2026", "attributes": { "label": "Behind Agentic Pull Requests: An Empirical Study on Developer Interventions in AI Agent-Authored Pull Requests", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Khelifi", "source": "https://espace2.etsmtl.ca/id/eprint/34495/", "contribution": "Human interventions occur on fewer agent PRs, but those interventions are often more extensive and guidance-oriented.", "limitation": "Metadata events cannot certify actual review quality; shared AIDev data.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://espace2.etsmtl.ca/id/eprint/34495/", "publication_status_note": "AIDev observational cohort reused; incomplete independence", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_PUBLICATION", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1145/3793302.3793586", "data_snapshot_warning": "Uses AIDev PR records.", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass3_audit_primary_url": "https://espace2.etsmtl.ca/id/eprint/34495/", "pass3_audit_version": "MSR 2026 published author copy pp.843-844", "pass3_audit_depth": "ORIGINAL_PAPER_METHODS_AND_TABLE_SELECTED", "pass3_audit_methods_locators": "Table 1 four human cells versus stated 5869; results tables", "pass3_audit_sample": "Repository-matched AIDev subset closed PRs; 5869 agent, stated 5869 human", "pass3_audit_observation": "Human count cells sum to 5853; mismatch 16; interventions 52.17/83.59% reported", "pass3_audit_boundary": "Unresolved missing records and observational selection; elapsed time is not reviewer labor", "pass3_audit_original_data_replication": "NO", "pass3_audit_provenance": "PASS3_PRINTED_EDITION_RECONSTRUCTED_2026-10-10", "pass3_audit_date": "2026-10-10", "pass6_date": "2026-10-10", "pass6_locator": "https://espace2.etsmtl.ca/id/eprint/34495/1/Ouni-A-2026-34495.pdf", "pass6_inspection_depth": "PUBLISHED_ACM_PROCEEDINGS_TABLE1_P2", "pass6_page_scope": "p2 Table1 and p1 methods", "pass6_finding": "HPR 5853 printed vs 5869 described; arithmetic-inferred final cell 261; 52.17/83.59% intervention margins", "pass6_limitation": "RAW_OBSERVATIONS_NOT_AVAILABLE", "pass6_original_data_replicated": "NO", "ndse2_actual_chapters_json": "[\"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Agent failure and escalation", "K:Human-agent collaboration", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W069", "label": "Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08", "C:C10" ], "printed": true, "summary": "The AI label increases fixation time without evidence that defect detection improves.", "limitation": "Identical human-origin code; injected-defect detection not assessed.", "url": "https://arxiv.org/abs/2606.26505", "authors": "Khojah", "year": "2026", "attributes": { "label": "Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Khojah", "source": "https://arxiv.org/abs/2606.26505", "contribution": "The AI label increases fixation time without evidence that defect detection improves.", "limitation": "Identical human-origin code; injected-defect detection not assessed.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:PRIMARY_ABSTRACT_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Automation bias and trust", "K:Independent verification and oracles", "K:Human cognitive load" ], "volumes": [ "V06" ] }, { "id": "W070", "label": "Impact of an LLM-based Review Assistant in Practice: A Mixed Open-/Closed-source Case Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "AI review comments have modest acceptance and must be filtered for relevance, especially functional advice.", "limitation": "Acceptance is a process proxy, not defect prevention.", "url": "https://arxiv.org/abs/2411.07091", "authors": "Olewicki", "year": "2026", "attributes": { "label": "Impact of an LLM-based Review Assistant in Practice: A Mixed Open-/Closed-source Case Study", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Olewicki", "source": "https://arxiv.org/abs/2411.07091", "contribution": "AI review comments have modest acceptance and must be filtered for relevance, especially functional advice.", "limitation": "Acceptance is a process proxy, not defect prevention.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:AI as reviewer" ], "volumes": [] }, { "id": "W071", "label": "Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:What agents can do" ], "actual": [ "C:C03", "C:C04", "C:C07", "C:C11" ], "mapped": [ "C:C03", "C:C04", "C:C07", "C:C08", "C:C11" ], "printed": true, "summary": "Rejection categories include agent failure, project workflow mismatch and unspecified reasons; distinguish causes before retrying.", "limitation": "Explanations may be inferred from inconsistent PR records; shared AIDev data.", "url": "https://arxiv.org/html/2605.22534", "authors": "Peralta", "year": "2026", "attributes": { "label": "Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Peralta", "source": "https://arxiv.org/html/2605.22534", "contribution": "Rejection categories include agent failure, project workflow mismatch and unspecified reasons; distinguish causes before retrying.", "limitation": "Explanations may be inferred from inconsistent PR records; shared AIDev data.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "AIDEV_DERIVED_OBSERVATIONAL_STRATIFIED_CODING", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "AIDEV_DERIVED_OBSERVATIONAL_STRATIFIED_CODING", "full_manuscript_audited": "yes_selected_methods", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/html/2605.22534", "publication_status_note": "2026 MSR paper, Sections 3-6; explicitly builds on AIDev", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "FULLTEXT_HTML_METHODS_TABLES", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_MANUSCRIPT_SECTIONS", "audit_locator": "MSR 2026 arXiv 2605.22534 html Sections 3-6 and Tables 1-3", "doi": "10.1145/3793302.3793575", "data_snapshot_warning": "Uses AIDev PR records (MSR 2026 Sect. 3), 9799 human-reviewed filtered PRs, 717 stratified manually assessed.", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C04\", \"C:C07\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Agent failure and escalation", "K:Specifications and governance", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W072", "label": "AI-to-AI Code Reviews of GitHub Pull Requests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "AI agents are already reviewing other agents, but automation density says nothing about independent error detection.", "limitation": "Distinct AI-to-AI actors rare, and quality not measured.", "url": "https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.75", "authors": "Selvanayagam", "year": "2026", "attributes": { "label": "AI-to-AI Code Reviews of GitHub Pull Requests", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Selvanayagam", "source": "https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.75", "contribution": "AI agents are already reviewing other agents, but automation density says nothing about independent error detection.", "limitation": "Distinct AI-to-AI actors rare, and quality not measured.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.75", "pass7_identity_source_class": "peer_reviewed_open_access", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W073", "label": "The Effect of Complexity and Provenance on Code Review Decisions: Evidence from a Controlled Experiment", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C05", "C:C07", "C:C08" ], "printed": true, "summary": "Complexity makes reviewers more likely to accept wrong changes; AI labeling alone has no significant outcome effect.", "limitation": "Controlled decisions rather than production incidents.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Singh", "year": "2026", "attributes": { "label": "The Effect of Complexity and Provenance on Code Review Decisions: Evidence from a Controlled Experiment", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Singh", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Complexity makes reviewers more likely to accept wrong changes; AI labeling alone has no significant outcome effect.", "limitation": "Controlled decisions rather than production incidents.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Review capacity and maintainers", "K:Technical debt and complexity", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W074", "label": "RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Productivity" ], "actual": [ "C:C08" ], "mapped": [ "C:C02", "C:C07", "C:C08" ], "printed": true, "summary": "AI-assisted review associates with shorter PR cycles and fewer human comments.", "limitation": "No defect-rate or deployed-incident endpoint.", "url": "https://arxiv.org/abs/2601.01129", "authors": "Tantithamthavorn", "year": "2026", "attributes": { "label": "RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Tantithamthavorn", "source": "https://arxiv.org/abs/2601.01129", "contribution": "AI-assisted review associates with shorter PR cycles and fewer human comments.", "limitation": "No defect-rate or deployed-incident endpoint.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:PRIMARY_ABSTRACT_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers" ], "volumes": [ "V06" ] }, { "id": "W075", "label": "Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in LLMs", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Models often correct an externally attributed mistake more successfully than their own.", "limitation": "Non-programming tasks; transfer to SWE is a hypothesis.", "url": "https://arxiv.org/abs/2507.02778", "authors": "Tsui", "year": "2026", "attributes": { "label": "Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in LLMs", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Tsui", "source": "https://arxiv.org/abs/2507.02778", "contribution": "Models often correct an externally attributed mistake more successfully than their own.", "limitation": "Non-programming tasks; transfer to SWE is a hypothesis.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:FULLTEXT_HTML", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Agent failure and escalation" ], "volumes": [] }, { "id": "W076", "label": "SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:What agents can do" ], "actual": [ "C:C08" ], "mapped": [ "C:C03", "C:C07", "C:C08", "C:C12" ], "printed": true, "summary": "Best model review approaches show limited precision and recall for verified review findings.", "limitation": "Benchmark is model-only, and human collaborative settings differ.", "url": "https://arxiv.org/abs/2509.01494", "authors": "Zeng", "year": "2026", "attributes": { "label": "SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Zeng", "source": "https://arxiv.org/abs/2509.01494", "contribution": "Best model review approaches show limited precision and recall for verified review findings.", "limitation": "Benchmark is model-only, and human collaborative settings differ.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:PRIMARY_ABSTRACT_CHECKED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Employment and early-career roles" ], "volumes": [ "V06" ] }, { "id": "W077", "label": "Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Code quality & security" ], "actual": [ "C:C04", "C:C07" ], "mapped": [ "C:C03", "C:C04", "C:C05", "C:C07", "C:C08" ], "printed": true, "summary": "Tests generated directly from defective implementations can encode the bug; an independent specification reduces error propagation.", "limitation": "Specific Java defect benchmark and prompt setup.", "url": "https://doi.org/10.1145/3832204", "authors": "Zhao", "year": "2026", "attributes": { "label": "Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Zhao", "source": "https://arxiv.org/abs/2607.22883", "contribution": "Tests generated directly from defective implementations can encode the bug; an independent specification reduces error propagation.", "limitation": "Specific Java defect benchmark and prompt setup.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "2026", "publication_source_url": "https://doi.org/10.1145/3832204", "publication_status_note": "Proceedings of the ACM on Software Engineering / ISSTA 2026", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH04:ABSTRACT_AND_REPOSITORY; CH07:PRIMARY_PDF_PAGE_CHECKED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C04\", \"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Specifications and governance", "K:Evaluation methodology and baselines", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W078", "label": "Beyond the Surface: Measuring Self-Preference in LLM Judgments", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Model and training-data similarity influence judgments, complicating same-model evaluator independence.", "limitation": "Text-based judgment tasks, not code reviews.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Chen", "year": "2025", "attributes": { "label": "Beyond the Surface: Measuring Self-Preference in LLM Judgments", "kind": "paper", "group": "Verification & review", "year": "2025", "lead_author": "Chen", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Model and training-data similarity influence judgments, complicating same-model evaluator independence.", "limitation": "Text-based judgment tasks, not code reviews.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:FULLTEXT_HTML_PUBLISHER", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:AI as reviewer", "K:Skills formation and teaching", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W079", "label": "Correlated Errors in Large Language Models", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C03", "C:C07", "C:C08" ], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Errors can be shared across models, so a second model is not automatically an independent checker.", "limitation": "General LLM datasets; may not predict specific coding errors.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Kim", "year": "2025", "attributes": { "label": "Correlated Errors in Large Language Models", "kind": "paper", "group": "Verification & review", "year": "2025", "lead_author": "Kim", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Errors can be shared across models, so a second model is not automatically an independent checker.", "limitation": "General LLM datasets; may not predict specific coding errors.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "Generic model error correlation (transfer hypothesis)", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH07:FULLTEXT_HTML_PUBLISHER; CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass3_audit_primary_url": "https://arxiv.org/html/2506.07962", "pass3_audit_version": "arXiv research preprint 2025", "pass3_audit_depth": "ORIGINAL_HTML_SELECTED_DESIGN", "pass3_audit_methods_locators": "Data/Methods and conditional-error calculation", "pass3_audit_sample": "349 models and 12032 MCQs on one leaderboard; 71 models/14042 questions on HELM", "pass3_audit_observation": "~60% same wrong answer conditional on both models wrong on HELM", "pass3_audit_boundary": "Not code-review or defect co-detection; cannot set checker correlation rate", "pass3_audit_original_data_replication": "NO", "pass3_audit_provenance": "PASS3_PRINTED_EDITION_RECONSTRUCTED_2026-10-10", "pass3_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C07\", \"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W080", "label": "Unit Testing Past vs. Present: Examining LLMs' Impact on Defect Detection and Efficiency", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C07" ], "mapped": [ "C:C07", "C:C08", "C:C12" ], "printed": true, "summary": "LLM-supported unit-test writing detects more bugs than an earlier unassisted cohort.", "limitation": "Non-random historical controls and learner population.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Ramler", "year": "2025", "attributes": { "label": "Unit Testing Past vs. Present: Examining LLMs' Impact on Defect Detection and Efficiency", "kind": "paper", "group": "Verification & review", "year": "2025", "lead_author": "Ramler", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "LLM-supported unit-test writing detects more bugs than an earlier unassisted cohort.", "limitation": "Non-random historical controls and learner population.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:FULLTEXT_HTML_PUBLISHER", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Economic costs and return", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W081", "label": "Deep Learning-based Code Reviews: A Paradigm Shift or a Double-Edged Sword?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Starting with LLM comments consumes more time without finding more major seeded defects.", "limitation": "Small controlled sample; one system, but true defects observable.", "url": "https://arxiv.org/abs/2411.11401", "authors": "Tufano", "year": "2025", "attributes": { "label": "Deep Learning-based Code Reviews: A Paradigm Shift or a Double-Edged Sword?", "kind": "paper", "group": "Verification & review", "year": "2025", "lead_author": "Tufano", "source": "https://arxiv.org/abs/2411.11401", "contribution": "Starting with LLM comments consumes more time without finding more major seeded defects.", "limitation": "Small controlled sample; one system, but true defects observable.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Skills formation and teaching", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W082", "label": "LLM Evaluators Recognize and Favor Their Own Generations", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C07" ], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "LLM judges recognize and favor their own prose generations, cautioning against self-grading loops.", "limitation": "Summarization benchmark, not code.", "url": "https://arxiv.org/abs/2404.13076", "authors": "Panickssery", "year": "2024", "attributes": { "label": "LLM Evaluators Recognize and Favor Their Own Generations", "kind": "paper", "group": "Verification & review", "year": "2024", "lead_author": "Panickssery", "source": "https://arxiv.org/abs/2404.13076", "contribution": "LLM judges recognize and favor their own prose generations, cautioning against self-grading loops.", "limitation": "Summarization benchmark, not code.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2024", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "Generic LLM-as-a-judge preference (transfer hypothesis)", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:FULLTEXT_HTML", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:AI as reviewer", "K:Benchmarks and construct validity" ], "volumes": [ "V06" ] }, { "id": "W083", "label": "A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C04", "C:C07", "C:C08", "C:C10" ], "printed": true, "summary": "Disclosing machine authorship increases inspection and improves code validation and repair in a small experiment.", "limitation": "Twenty-eight participants; different from passive label studies.", "url": "https://arxiv.org/abs/2405.16081", "authors": "Tang", "year": "2024", "attributes": { "label": "A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions", "kind": "paper", "group": "Verification & review", "year": "2024", "lead_author": "Tang", "source": "https://arxiv.org/abs/2405.16081", "contribution": "Disclosing machine authorship increases inspection and improves code validation and repair in a small experiment.", "limitation": "Twenty-eight participants; different from passive label studies.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2024", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Specifications and governance", "K:Human cognitive load", "K:Ownership and knowledge transfer" ], "volumes": [ "V06" ] }, { "id": "W084", "label": "Self-Preference Bias in LLM-as-a-Judge", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C02", "C:C07", "C:C08" ], "printed": true, "summary": "Judges favor model-familiar outputs; stylistic similarity can masquerade as quality.", "limitation": "Dialogue judgments, not production software.", "url": "https://arxiv.org/abs/2410.21819", "authors": "Wataoka", "year": "2024", "attributes": { "label": "Self-Preference Bias in LLM-as-a-Judge", "kind": "paper", "group": "Verification & review", "year": "2024", "lead_author": "Wataoka", "source": "https://arxiv.org/abs/2410.21819", "contribution": "Judges favor model-familiar outputs; stylistic similarity can masquerade as quality.", "limitation": "Dialogue judgments, not production software.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2024", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:AI as reviewer" ], "volumes": [] }, { "id": "W085", "label": "Automation Bias in Mammography: The Impact of Artificial Intelligence BI-RADS Suggestions on Reader Performance", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C07", "C:C08", "C:C10" ], "printed": true, "summary": "Even expert readers follow wrong AI suggestions, supporting a general need for calibrated skepticism.", "limitation": "Clinical imaging analogy, not direct SWE evidence.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Dratsch", "year": "2023", "attributes": { "label": "Automation Bias in Mammography: The Impact of Artificial Intelligence BI-RADS Suggestions on Reader Performance", "kind": "paper", "group": "Verification & review", "year": "2023", "lead_author": "Dratsch", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Even expert readers follow wrong AI suggestions, supporting a general need for calibrated skepticism.", "limitation": "Clinical imaging analogy, not direct SWE evidence.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2023", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "Clinical mammography automation bias, not source review", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass6_primary_locator": "https://pubs.rsna.org/doi/10.1148/radiol.222176", "pass6_metadata_depth": "PUBLISHED_PEER_REVIEWED_JOURNAL_DOI", "pass6_supporting_locator": "https://pubmed.ncbi.nlm.nih.gov/37129490/", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust" ], "volumes": [] }, { "id": "W086", "label": "Quality Evaluation of Modern Code Reviews Through Intelligent Biometric Program Comprehension", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C07", "C:C08", "C:C09", "C:C10" ], "printed": true, "summary": "Physiological signals may be correlated with quality of code review rather than just speed.", "limitation": "Sample size in bibliography unverified; invasive and nonstandard.", "url": "https://doi.org/10.1109/TSE.2022.3158543", "authors": "Hijazi", "year": "2023", "attributes": { "label": "Quality Evaluation of Modern Code Reviews Through Intelligent Biometric Program Comprehension", "kind": "paper", "group": "Verification & review", "year": "2023", "lead_author": "Hijazi", "source": "https://doi.org/10.1109/TSE.2022.3158543", "contribution": "Physiological signals may be correlated with quality of code review rather than just speed.", "limitation": "Sample size in bibliography unverified; invasive and nonstandard.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2023", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1109/TSE.2022.3158543", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Human cognitive load", "K:System understanding and rationale", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W087", "label": "Do as AI say: susceptibility in deployment of clinical decision-aids", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Incorrect AI-attributed advice induces substantial errors even when professionals are experienced.", "limitation": "Clinical advice, not code review.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Gaube", "year": "2021", "attributes": { "label": "Do as AI say: susceptibility in deployment of clinical decision-aids", "kind": "paper", "group": "Verification & review", "year": "2021", "lead_author": "Gaube", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Incorrect AI-attributed advice induces substantial errors even when professionals are experienced.", "limitation": "Clinical advice, not code review.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2021", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "Clinical decision-aid behavior, not source review", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass6_primary_locator": "https://www.nature.com/articles/s41746-021-00385-9", "pass6_metadata_depth": "PUBLISHED_PEER_REVIEWED_JOURNAL_DOI", "pass6_supporting_locator": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7896064/", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles" ], "volumes": [] }, { "id": "W088", "label": "Trustworthiness Perceptions in Code Review: An Eye-tracking Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08", "C:C10" ], "printed": true, "summary": "Source labeling changes gaze and subjective ratings without demonstrating accuracy changes.", "limitation": "Ten students; predates current code LLMs.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Bertram", "year": "2020", "attributes": { "label": "Trustworthiness Perceptions in Code Review: An Eye-tracking Study", "kind": "paper", "group": "Verification & review", "year": "2020", "lead_author": "Bertram", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Source labeling changes gaze and subjective ratings without demonstrating accuracy changes.", "limitation": "Ten students; predates current code LLMs.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2020", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Review capacity and maintainers", "K:Automation bias and trust", "K:Human cognitive load", "K:Skills formation and teaching" ], "volumes": [ "V06" ] }, { "id": "W089", "label": "The Role of Domain Expertise in User Trust and the Impact of First Impressions with Intelligent Systems", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C03", "C:C07", "C:C08", "C:C10" ], "printed": true, "summary": "Expertise improves error recognition and trust calibration; initial failures shape later trust.", "limitation": "Arthropod classification, not code.", "url": "https://ojs.aaai.org/index.php/HCOMP/article/view/7469", "authors": "Nourani", "year": "2020", "attributes": { "label": "The Role of Domain Expertise in User Trust and the Impact of First Impressions with Intelligent Systems", "kind": "paper", "group": "Verification & review", "year": "2020", "lead_author": "Nourani", "source": "https://ojs.aaai.org/index.php/HCOMP/article/view/7469", "contribution": "Expertise improves error recognition and trust calibration; initial failures shape later trust.", "limitation": "Arthropod classification, not code.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2020", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "Non-code classifier trust experiment", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://ojs.aaai.org/index.php/HCOMP/article/view/7469", "pass7_identity_source_class": "publisher_record", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust", "K:Agent failure and escalation" ], "volumes": [] }, { "id": "W090", "label": "Decoding the Representation of Code in the Brain: An fMRI Study of Code Review and Expertise", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C07", "C:C08", "C:C09", "C:C10" ], "printed": true, "summary": "Code and prose review rely on distinguishable cognitive processes influenced by expertise.", "limitation": "Neural classification does not measure review effectiveness in production.", "url": "https://doi.org/10.1109/ICSE.2017.24", "authors": "Floyd", "year": "2017", "attributes": { "label": "Decoding the Representation of Code in the Brain: An fMRI Study of Code Review and Expertise", "kind": "paper", "group": "Verification & review", "year": "2017", "lead_author": "Floyd", "source": "https://doi.org/10.1109/ICSE.2017.24", "contribution": "Code and prose review rely on distinguishable cognitive processes influenced by expertise.", "limitation": "Neural classification does not measure review effectiveness in production.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2017", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1109/ICSE.2017.24", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Human cognitive load", "K:System understanding and rationale", "K:Economic costs and return", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W091", "label": "Automation bias and verification complexity: a systematic review", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C05", "C:C07", "C:C08" ], "printed": true, "summary": "Bias can arise in single verification tasks and increases with difficult-to-check suggestions.", "limitation": "Literature not directly about code.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7651899/", "authors": "Lyell", "year": "2017", "attributes": { "label": "Automation bias and verification complexity: a systematic review", "kind": "paper", "group": "Verification & review", "year": "2017", "lead_author": "Lyell", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7651899/", "contribution": "Bias can arise in single verification tasks and increases with difficult-to-check suggestions.", "limitation": "Literature not directly about code.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Literature synthesis", "editorial_priority": "B", "bibliography_year": "2017", "original_evidence_class": "Literature synthesis", "reviewed_evidence_class": "Literature synthesis", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "Cross-domain automation bias systematic review", "publication_year_from_independent_source": "", "publication_source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7651899/", "publication_status_note": "Systematic review of decision-support bias in healthcare/human factors; no direct AI software experiment", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "INDEXED_PRIMARY_JOURNAL_TEXT", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1093/jamia/ocw105", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust", "K:Independent verification and oracles", "K:Technical debt and complexity" ], "volumes": [ "V06" ] }, { "id": "W092", "label": "Complacency and Bias in Human Use of Automation: An Attentional Integration", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Automation-induced attention changes persist even among experienced professionals, motivating active verification design.", "limitation": "Legacy automation settings; extrapolation to coding agents must be tested.", "url": "https://doi.org/10.1177/0018720810376055", "authors": "Parasuraman", "year": "2010", "attributes": { "label": "Complacency and Bias in Human Use of Automation: An Attentional Integration", "kind": "paper", "group": "Verification & review", "year": "2010", "lead_author": "Parasuraman", "source": "https://doi.org/10.1177/0018720810376055", "contribution": "Automation-induced attention changes persist even among experienced professionals, motivating active verification design.", "limitation": "Legacy automation settings; extrapolation to coding agents must be tested.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2010", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1177/0018720810376055", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:System understanding and rationale" ], "volumes": [] }, { "id": "W093", "label": "Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C06", "C:C07", "C:C08", "C:C12" ], "printed": true, "summary": "Risk-ranked PR changes may permit selective automation and reserve reviewer time for consequential changes.", "limitation": "Production risk calibration requires independent defect outcomes and monitoring.", "url": "https://arxiv.org/abs/2605.30208", "authors": "Adams", "year": "2026", "attributes": { "label": "Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Adams", "source": "https://arxiv.org/abs/2605.30208", "contribution": "Risk-ranked PR changes may permit selective automation and reserve reviewer time for consequential changes.", "limitation": "Production risk calibration requires independent defect outcomes and monitoring.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2605.30208", "publication_status_note": "Original preprint; no full evaluation replicated", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Vulnerability and secure code", "K:Economic costs and return" ], "volumes": [ "V06" ] }, { "id": "W094", "label": "AI Slop is DDoSing Open Source: Understanding the Impact of AI-Generated Contributions on Open Source Sustainability", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Engineering structure" ], "actual": [ "C:C08", "C:C11" ], "mapped": [ "C:C03", "C:C07", "C:C08", "C:C11" ], "printed": true, "summary": "Influx of machine-generated submissions can increase maintainer load and lower merge propensity.", "limitation": "Attribution and matching complexity; context-dependent.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Afroz", "year": "2026", "attributes": { "label": "AI Slop is DDoSing Open Source: Understanding the Impact of AI-Generated Contributions on Open Source Sustainability", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Afroz", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Influx of machine-generated submissions can increase maintainer load and lower merge propensity.", "limitation": "Attribution and matching complexity; context-dependent.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING; CH11:ORIGINAL_PDF_METHODS_AND_TABLES", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Agent failure and escalation", "K:Technical debt and complexity", "K:System understanding and rationale", "K:Agent context and persistent memory" ], "volumes": [ "V06" ] }, { "id": "W095", "label": "Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Economics" ], "actual": [ "C:C03", "C:C07", "C:C12" ], "mapped": [ "C:C01", "C:C02", "C:C03", "C:C05", "C:C07", "C:C08", "C:C11", "C:C12" ], "printed": true, "summary": "Proposes analyzing the whole agentic lifecycle across verification reliability and cost.", "limitation": "Synthesis only, no new outcome dataset.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Bhati", "year": "2026", "attributes": { "label": "Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Bhati", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Proposes analyzing the whole agentic lifecycle across verification reliability and cost.", "limitation": "Synthesis only, no new outcome dataset.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH07:FULLTEXT_HTML; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass3_audit_primary_url": "https://arxiv.org/html/2609.04681", "pass3_audit_version": "arXiv research synthesis September 2026", "pass3_audit_depth": "PRIMARY_SYNTHESIS_CLASSIFICATION", "pass3_audit_methods_locators": "Abstract and evidence citations", "pass3_audit_sample": "No independent empirical sample", "pass3_audit_observation": "Discusses verification/cost; cites W003 prior field experiment", "pass3_audit_boundary": "Synthesis cannot become an independent replication of W003", "pass3_audit_original_data_replication": "NO", "pass3_audit_provenance": "PASS3_PRINTED_EDITION_RECONSTRUCTED_2026-10-10", "pass3_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C07\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Architecture and modularity", "K:Skills formation and teaching", "K:Economic costs and return", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W096", "label": "Go Home Copilot, You're Drunk: Understanding Developer Responses to Agent-Generated Code Review Comments", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Developer resolution rates differ across reviewing agents and ignore comments that conflict with intended design.", "limitation": "Resolution is not necessarily acceptance or correctness.", "url": "https://arxiv.org/abs/2607.21997", "authors": "Cynthia", "year": "2026", "attributes": { "label": "Go Home Copilot, You're Drunk: Understanding Developer Responses to Agent-Generated Code Review Comments", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Cynthia", "source": "https://arxiv.org/abs/2607.21997", "contribution": "Developer resolution rates differ across reviewing agents and ignore comments that conflict with intended design.", "limitation": "Resolution is not necessarily acceptance or correctness.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Review capacity and maintainers", "K:AI as reviewer", "K:Independent verification and oracles", "K:System understanding and rationale" ], "volumes": [ "V06" ] }, { "id": "W097", "label": "Programmers Are Poor and Overconfident Judges of LLM-Generated Assertions", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C04", "C:C07" ], "mapped": [ "C:C04", "C:C07", "C:C08" ], "printed": true, "summary": "Programmers inadequately spot bad AI assertions while remaining confident, questioning model-generated test oracles.", "limitation": "Short Python assertions and 86 participants.", "url": "https://arxiv.org/abs/2607.08885", "authors": "Kaufman", "year": "2026", "attributes": { "label": "Programmers Are Poor and Overconfident Judges of LLM-Generated Assertions", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Kaufman", "source": "https://arxiv.org/abs/2607.08885", "contribution": "Programmers inadequately spot bad AI assertions while remaining confident, questioning model-generated test oracles.", "limitation": "Short Python assertions and 86 participants.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH04:ABSTRACT; CH07:PRIMARY_PDF_ABSTRACT_PAGE_CHECKED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C04\", \"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:AI as reviewer", "K:Automation bias and trust", "K:Independent verification and oracles", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W098", "label": "Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Developers reject many AI reviewer comments, chiefly for false positives and irrelevance.", "limitation": "Only comments that received replies, inducing response-selection bias.", "url": "https://arxiv.org/abs/2607.03316", "authors": "Lin", "year": "2026", "attributes": { "label": "Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Lin", "source": "https://arxiv.org/abs/2607.03316", "contribution": "Developers reject many AI reviewer comments, chiefly for false positives and irrelevance.", "limitation": "Only comments that received replies, inducing response-selection bias.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:AI as reviewer" ], "volumes": [ "V06" ] }, { "id": "W099", "label": "From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C04", "C:C07", "C:C08" ], "mapped": [ "C:C01", "C:C03", "C:C04", "C:C07", "C:C08", "C:C11" ], "printed": true, "summary": "Comparing diff content to stated intent can help authors find unintended deviations.", "limitation": "Small reported effect; defect denominator absent.", "url": "https://arxiv.org/abs/2607.29516", "authors": "Maddila", "year": "2026", "attributes": { "label": "From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Maddila", "source": "https://arxiv.org/abs/2607.29516", "contribution": "Comparing diff content to stated intent can help authors find unintended deviations.", "limitation": "Small reported effect; defect denominator absent.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH04:ABSTRACT; CH07:FULLTEXT_HTML; CH08:FULL_TEXT_AUDIT_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "4", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass3_audit_primary_url": "https://arxiv.org/html/2607.29516v1", "pass3_audit_version": "arXiv:2607.29516v1 (2026-08-14)", "pass3_audit_depth": "ORIGINAL_HTML_SELECTED_METHODS_AND_TABLES", "pass3_audit_methods_locators": "Intent Table 3; drift Table 4; rollout Table 8", "pass3_audit_sample": "121 intent cases, 118 balanced drift cases; opt-in enterprise rollout", "pass3_audit_observation": "Intent F1 .860/.844; 52191/8089 tokens; drift exact 64.4%; reversions .33/.17%", "pass3_audit_boundary": "Selected self-attesting cohort not randomized; differing outcomes and sample sizes", "pass3_audit_original_data_replication": "NO", "pass3_audit_provenance": "PASS3_PRINTED_EDITION_RECONSTRUCTED_2026-10-10", "pass3_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C04\", \"C:C07\", \"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:AI as reviewer", "K:Agent failure and escalation", "K:Specifications and governance", "K:Long-running agent execution" ], "volumes": [ "V06" ] }, { "id": "W100", "label": "The End of Code Review: Coding Agents Supersede Human Inspection", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Challenges human-only review and motivates automatic verification research.", "limitation": "No empirical testing; should be presented as contested prediction.", "url": "https://arxiv.org/abs/2606.13175", "authors": "Monperrus", "year": "2026", "attributes": { "label": "The End of Code Review: Coding Agents Supersede Human Inspection", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Monperrus", "source": "https://arxiv.org/abs/2606.13175", "contribution": "Challenges human-only review and motivates automatic verification research.", "limitation": "No empirical testing; should be presented as contested prediction.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles" ], "volumes": [] }, { "id": "W101", "label": "Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:What agents can do" ], "actual": [ "C:C03", "C:C07" ], "mapped": [ "C:C03", "C:C04", "C:C07", "C:C08", "C:C09" ], "printed": true, "summary": "Models can explain a semantic migration rule and still miss behavior changes in their own port.", "limitation": "Small Python migration traps; individual model variation high.", "url": "https://arxiv.org/abs/2605.21537", "authors": "Purnachandra Reddy", "year": "2026", "attributes": { "label": "Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Purnachandra Reddy", "source": "https://arxiv.org/abs/2605.21537", "contribution": "Models can explain a semantic migration rule and still miss behavior changes in their own port.", "limitation": "Small Python migration traps; individual model variation high.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH07:FULLTEXT_HTML", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:AI as reviewer", "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Agent failure and escalation", "K:Agent context and persistent memory" ], "volumes": [ "V06" ] }, { "id": "W102", "label": "Cross-Model LLM Code Review: Should You Use Claude to Review Codex or Vice Versa?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Independent model review helps some model orderings but can worsen an already strong implementation.", "limitation": "Two models, narrow benchmark, multiple comparisons.", "url": "https://arxiv.org/abs/2607.21656", "authors": "Xiang", "year": "2026", "attributes": { "label": "Cross-Model LLM Code Review: Should You Use Claude to Review Codex or Vice Versa?", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Xiang", "source": "https://arxiv.org/abs/2607.21656", "contribution": "Independent model review helps some model orderings but can worsen an already strong implementation.", "limitation": "Two models, narrow benchmark, multiple comparisons.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Controlled benchmark; complete-case subset, not human field trial", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:PRIMARY_PDF_PAGE_CHECKED; CH08:PRIMARY_ABSTRACT_CHECKED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass2_source_locator": "https://arxiv.org/html/2607.21656", "pass2_source_version": "arXiv 2607.21656v1 2026-07-22", "pass2_inspection_scope": "Sections 3.1--3.4 4.1--4.4 Tables 2 and 4", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Controlled benchmark with complete-case task selection", "pass2_critical_limitation": "No human review; model cannot run tests during review; complete cases and specific model pricing; not repo representative", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W103", "label": "An Eye for Trust: An Exploration of Developers' Trust Perceptions Through Urgency and Reputation", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08", "C:C10", "C:C12" ], "printed": true, "summary": "Deadline and perceived seniority alter visual review effort more than final decisions.", "limitation": "Source labels manipulated; performance unchanged.", "url": "https://arxiv.org/abs/2604.08713", "authors": "Yabesi", "year": "2026", "attributes": { "label": "An Eye for Trust: An Exploration of Developers' Trust Perceptions Through Urgency and Reputation", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Yabesi", "source": "https://arxiv.org/abs/2604.08713", "contribution": "Deadline and perceived seniority alter visual review effort more than final decisions.", "limitation": "Source labels manipulated; performance unchanged.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Automation bias and trust", "K:Human cognitive load", "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W104", "label": "Coding with Enemy: Can Human Developers Detect AI Agent Sabotage?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:Code quality & security" ], "actual": [ "C:C06", "C:C08" ], "mapped": [ "C:C03", "C:C05", "C:C06", "C:C07", "C:C08" ], "printed": true, "summary": "Most users miss covert exfiltration behavior, and alerts alone often fail to prevent acceptance.", "limitation": "Simulated malicious-agent setting, not baseline prevalence.", "url": "https://arxiv.org/abs/2606.05647", "authors": "Ye", "year": "2026", "attributes": { "label": "Coding with Enemy: Can Human Developers Detect AI Agent Sabotage?", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Ye", "source": "https://arxiv.org/abs/2606.05647", "contribution": "Most users miss covert exfiltration behavior, and alerts alone often fail to prevent acceptance.", "limitation": "Simulated malicious-agent setting, not baseline prevalence.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH06:SOURCE_LOCATOR_ONLY; CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C06\", \"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Agent failure and escalation", "K:Prompt injection and malicious tools", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W105", "label": "Beyond Lexical Metrics: Sentence-Embedding Detection of Reviewer Habituation in AI Code Review", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Reviewers approve more agent PRs over time, but changes in detection of defects remain unknown.", "limitation": "Selection, learning and project dynamics can mimic habituation.", "url": "https://arxiv.org/abs/2609.06213", "authors": "Yu", "year": "2026", "attributes": { "label": "Beyond Lexical Metrics: Sentence-Embedding Detection of Reviewer Habituation in AI Code Review", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Yu", "source": "https://arxiv.org/abs/2609.06213", "contribution": "Reviewers approve more agent PRs over time, but changes in detection of defects remain unknown.", "limitation": "Selection, learning and project dynamics can mimic habituation.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Automation bias and trust", "K:Skills formation and teaching", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W106", "label": "Code Review Agent Benchmark (c-CRAB)", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:What agents can do" ], "actual": [ "C:C08" ], "mapped": [ "C:C03", "C:C05", "C:C07", "C:C08" ], "printed": true, "summary": "Multiple agent reviewers fail most human-identified actionable review checks, especially architectural issues.", "limitation": "Human ground truth built into benchmark by construction.", "url": "https://arxiv.org/abs/2603.23448", "authors": "Zhang", "year": "2026", "attributes": { "label": "Code Review Agent Benchmark (c-CRAB)", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Zhang", "source": "https://arxiv.org/abs/2603.23448", "contribution": "Multiple agent reviewers fail most human-identified actionable review checks, especially architectural issues.", "limitation": "Human ground truth built into benchmark by construction.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Benchmarks and construct validity", "K:Architecture and modularity" ], "volumes": [ "V06" ] }, { "id": "W107", "label": "Human-AI Synergy in Agentic Code Review", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [ "C:C08" ], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Human-on-agent discussions are longer and AI-reviewer suggestions adopted much less than human ones.", "limitation": "Observes only PRs with discussions; not controlled.", "url": "https://arxiv.org/abs/2603.15911", "authors": "Zhong", "year": "2026", "attributes": { "label": "Human-AI Synergy in Agentic Code Review", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Zhong", "source": "https://arxiv.org/abs/2603.15911", "contribution": "Human-on-agent discussions are longer and AI-reviewer suggestions adopted much less than human ones.", "limitation": "Observes only PRs with discussions; not controlled.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W108", "label": "Do LLM Evaluators Prefer Themselves for a Reason?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C02", "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Some model self preference reflects genuine quality, but biased acceptance of its own wrong answers persists.", "limitation": "Code benchmark limited to MBPP+, not production PRs.", "url": "https://arxiv.org/abs/2504.03846", "authors": "Chen", "year": "2025", "attributes": { "label": "Do LLM Evaluators Prefer Themselves for a Reason?", "kind": "paper", "group": "Verification & review", "year": "2025", "lead_author": "Chen", "source": "https://arxiv.org/abs/2504.03846", "contribution": "Some model self preference reflects genuine quality, but biased acceptance of its own wrong answers persists.", "limitation": "Code benchmark limited to MBPP+, not production PRs.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:AI as reviewer", "K:Independent verification and oracles", "K:Benchmarks and construct validity" ], "volumes": [] }, { "id": "W109", "label": "LLM Critics Help Catch LLM Bugs", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:What agents can do" ], "actual": [ "C:C08" ], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Model critics can help identify injected defects, especially combined with human scrutiny.", "limitation": "Compared against contractors reviewing snippets without repository knowledge.", "url": "https://arxiv.org/abs/2407.00215", "authors": "McAleese", "year": "2024", "attributes": { "label": "LLM Critics Help Catch LLM Bugs", "kind": "paper", "group": "Verification & review", "year": "2024", "lead_author": "McAleese", "source": "https://arxiv.org/abs/2407.00215", "contribution": "Model critics can help identify injected defects, especially combined with human scrutiny.", "limitation": "Compared against contractors reviewing snippets without repository knowledge.", "manual_use": "Separate reviewer effort, comment usefulness and defect detection.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2024", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:AI as reviewer", "K:Automation bias and trust" ], "volumes": [ "V06" ] }, { "id": "W110", "label": "Overreliance on AI: Literature Review", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review" ], "actual": [], "mapped": [ "C:C07", "C:C08" ], "printed": true, "summary": "Expert skepticism expressed in surveys need not predict actual reliance on automation.", "limitation": "Review not focused on coding.", "url": "https://www.microsoft.com/en-us/research/publication/overreliance-on-ai-literature-review/", "authors": "Passi", "year": "2022", "attributes": { "label": "Overreliance on AI: Literature Review", "kind": "paper", "group": "Verification & review", "year": "2022", "lead_author": "Passi", "source": "https://www.microsoft.com/en-us/research/publication/overreliance-on-ai-literature-review/", "contribution": "Expert skepticism expressed in surveys need not predict actual reliance on automation.", "limitation": "Review not focused on coding.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2022", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://www.microsoft.com/en-us/research/publication/overreliance-on-ai-literature-review/", "pass7_identity_source_class": "institutional_technical_report", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust" ], "volumes": [] }, { "id": "W111", "label": "Many SWE-bench-Passing PRs Would Not Be Merged into Main", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Verification & review", "T:What agents can do" ], "actual": [ "C:C03", "C:C07", "C:C08" ], "mapped": [ "C:C03", "C:C04", "C:C07", "C:C08" ], "printed": true, "summary": "Automated benchmark passage overestimates practical merge-readiness for single-attempt agent patches.", "limitation": "Agent had no reviewer feedback/CI; benchmark is not complete agent capability.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "authors": "Whitfill", "year": "2026", "attributes": { "label": "Many SWE-bench-Passing PRs Would Not Be Merged into Main", "kind": "paper", "group": "Verification & review", "year": "2026", "lead_author": "Whitfill", "source": "https://www.sepolimi.com/p/se-ai-bibliography-verification-review", "contribution": "Automated benchmark passage overestimates practical merge-readiness for single-attempt agent patches.", "limitation": "Agent had no reviewer feedback/CI; benchmark is not complete agent capability.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH07:PRIMARY_HTML_INSPECTED; CH08:FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://metr.org/notes/2026-03-10-many-swe-bench-passing-prs-would-not-be-merged-into-main/", "pass4_audit_version": "METR original research note (2026-03-10)", "pass4_audit_depth": "ORIGINAL_HTML_METHODS_AND_RESULTS_SELECTED", "pass4_audit_methods_locators": "Data/Methods, reviewer protocol, figures 1-3, uncertainty caveat", "pass4_audit_sample": "4 maintainers, 3 of 12 repos, 95 tasks, 296 AI patch reviews and 47 gold patches", "pass4_audit_observation": "Automatic grader merge-decision gap 24.2 pp (SE 2.7); gold-baseline merge 68%", "pass4_audit_boundary": "Review hypothetically in historical repos, no CI or iterative developer feedback; cluster/generalization limits", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C07\", \"C:C08\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Independent verification and oracles", "K:Benchmarks and construct validity" ], "volumes": [ "V06" ] }, { "id": "W112", "label": "Novice Developers Produce Larger Review Overhead for Project Maintainers while Vibe Coding", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Verification & review" ], "actual": [ "C:C10", "C:C11" ], "mapped": [ "C:C08", "C:C10", "C:C11" ], "printed": true, "summary": "Inexperienced agent-tool contributors impose disproportionate maintainer review effort and receive lower acceptance.", "limitation": "Experience classification and PR selection limit causal inference.", "url": "https://arxiv.org/abs/2602.23905", "authors": "Asdaque", "year": "2026", "attributes": { "label": "Novice Developers Produce Larger Review Overhead for Project Maintainers while Vibe Coding", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Asdaque", "source": "https://arxiv.org/abs/2602.23905", "contribution": "Inexperienced agent-tool contributors impose disproportionate maintainer review effort and receive lower acceptance.", "limitation": "Experience classification and PR selection limit causal inference.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Review capacity and maintainers", "K:Skills formation and teaching", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W113", "label": "I Would Have Written My Code Differently: Beginners Struggle to Understand LLM-Generated Code", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Verification & review" ], "actual": [ "C:C10" ], "mapped": [ "C:C04", "C:C08", "C:C10", "C:C11" ], "printed": true, "summary": "Novices cannot reliably tell whether generated programs satisfy plain-language intent.", "limitation": "Introductory students and short Python tasks; not professionals.", "url": "https://arxiv.org/abs/2504.19037", "authors": "Zi", "year": "2025", "attributes": { "label": "I Would Have Written My Code Differently: Beginners Struggle to Understand LLM-Generated Code", "kind": "paper", "group": "Skills & learning", "year": "2025", "lead_author": "Zi", "source": "https://arxiv.org/abs/2504.19037", "contribution": "Novices cannot reliably tell whether generated programs satisfy plain-language intent.", "limitation": "Introductory students and short Python tasks; not professionals.", "manual_use": "Design exercises that retain comprehension and calibrated independent judgment.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:ARXIV_PDF_PAGES_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Specifications and governance", "K:Human cognitive load", "K:Skills formation and teaching", "K:System understanding and rationale" ], "volumes": [ "V06" ] }, { "id": "W114", "label": "Correlates of programmer efficacy and their link to experience: a combined EEG and eye-tracking study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:System knowledge & memory" ], "actual": [ "C:C10" ], "mapped": [ "C:C09", "C:C10", "C:C11" ], "printed": true, "summary": "Selective code reading and cognitive engagement predict efficacy better than crude years-of-experience indicators.", "limitation": "Thirty-seven programmers; correlation not pedagogy intervention.", "url": "https://doi.org/10.1145/3540250.3549084", "authors": "Peitek", "year": "2022", "attributes": { "label": "Correlates of programmer efficacy and their link to experience: a combined EEG and eye-tracking study", "kind": "paper", "group": "Skills & learning", "year": "2022", "lead_author": "Peitek", "source": "https://doi.org/10.1145/3540250.3549084", "contribution": "Selective code reading and cognitive engagement predict efficacy better than crude years-of-experience indicators.", "limitation": "Thirty-seven programmers; correlation not pedagogy intervention.", "manual_use": "Design exercises that retain comprehension and calibrated independent judgment.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2022", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://doi.org/10.1145/3540250.3549084", "publication_status_note": "2022 conference version; arXiv uploaded 2023; full text pending", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PUBLISHER_DOI_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1145/3540250.3549084", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:Cognitive offloading and skill debt" ], "volumes": [ "V06" ] }, { "id": "W115", "label": "Novice Software Developers, All Over Again", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Newly hired developers spend substantial time communicating and reconstructing team knowledge.", "limitation": "Eight graduates in one company; predates AI.", "url": "https://www.microsoft.com/en-us/research/publication/novice-software-developers-all-over-again/", "authors": "Begel", "year": "2008", "attributes": { "label": "Novice Software Developers, All Over Again", "kind": "paper", "group": "Skills & learning", "year": "2008", "lead_author": "Begel", "source": "https://www.microsoft.com/en-us/research/publication/novice-software-developers-all-over-again/", "contribution": "Newly hired developers spend substantial time communicating and reconstructing team knowledge.", "limitation": "Eight graduates in one company; predates AI.", "manual_use": "Design exercises that retain comprehension and calibrated independent judgment.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2008", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://www.microsoft.com/en-us/research/publication/novice-software-developers-all-over-again/", "publication_status_note": "2008 developer onboarding, pre-AI context", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_PUBLICATION", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1145/1404520.1404522", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Skills formation and teaching", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W116", "label": "Using Biometrics to Understand AI-Assisted Coding Performance and its Perception", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Verification & review" ], "actual": [ "C:C10" ], "mapped": [ "C:C07", "C:C08", "C:C10", "C:C11" ], "printed": true, "summary": "Physiological signals under AI assistance suggest reduced engagement despite apparent code-generation progress.", "limitation": "Students, two writing tasks and different unverified signal endpoints.", "url": "https://arxiv.org/abs/2606.20598", "authors": "Burelli", "year": "2026", "attributes": { "label": "Using Biometrics to Understand AI-Assisted Coding Performance and its Perception", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Burelli", "source": "https://arxiv.org/abs/2606.20598", "contribution": "Physiological signals under AI assistance suggest reduced engagement despite apparent code-generation progress.", "limitation": "Students, two writing tasks and different unverified signal endpoints.", "manual_use": "Design exercises that retain comprehension and calibrated independent judgment.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Human cognitive load", "K:Skills formation and teaching", "K:Cognitive offloading and skill debt", "K:System understanding and rationale" ], "volumes": [ "V06" ] }, { "id": "W117", "label": "The Augmentation Trap: AI Productivity and the Cost of Cognitive Offloading", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Economics" ], "actual": [ "C:C10" ], "mapped": [ "C:C02", "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Short-run assistance can undermine incentives to acquire knowledge and create delayed productivity costs.", "limitation": "Theoretical mechanism needs longitudinal field validation.", "url": "https://arxiv.org/abs/2604.03501", "authors": "Caosun", "year": "2026", "attributes": { "label": "The Augmentation Trap: AI Productivity and the Cost of Cognitive Offloading", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Caosun", "source": "https://arxiv.org/abs/2604.03501", "contribution": "Short-run assistance can undermine incentives to acquire knowledge and create delayed productivity costs.", "limitation": "Theoretical mechanism needs longitudinal field validation.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2604.03501", "publication_status_note": "Theoretical/economic model, NOT a randomized programming outcome", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Human cognitive load", "K:Cognitive offloading and skill debt", "K:Economic costs and return" ], "volumes": [ "V06" ] }, { "id": "W118", "label": "How AI Impacts Skill Formation", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Productivity" ], "actual": [ "C:C10" ], "mapped": [ "C:C02", "C:C07", "C:C10", "C:C11" ], "printed": true, "summary": "Access to AI can reduce independent conceptual learning even without faster task completion.", "limitation": "Controlled learning quiz; not long-run professional performance. Immediate quiz only, not delayed retention. Source percentage normalization is unresolved; Figure 10.2 is qualitative. See Appendix B and ISSUE:V6:W118_NORMALIZATION.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-skills-learning", "authors": "Shen", "year": "2026", "attributes": { "label": "How AI Impacts Skill Formation", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Shen", "source": "https://www.sepolimi.com/p/se-ai-bibliography-skills-learning", "contribution": "Access to AI can reduce independent conceptual learning even without faster task completion.", "limitation": "Controlled learning quiz; not long-run professional performance.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Controlled human or field experiment", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:ARXIV_V2_PDF_PAGES_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Independent verification and oracles", "K:Skills formation and teaching", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W119", "label": "Training in the Age of AI: A Theory of Career Viability", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Jobs & roles" ], "actual": [ "C:C10", "C:C12" ], "mapped": [ "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Automation of junior work may erode apprenticeship and reduce the future skilled-worker pipeline.", "limitation": "Model predictions, not observed labor dynamics.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-skills-learning", "authors": "Garicano", "year": "2026", "attributes": { "label": "Training in the Age of AI: A Theory of Career Viability", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Garicano", "source": "https://www.sepolimi.com/p/se-ai-bibliography-skills-learning", "contribution": "Automation of junior work may erode apprenticeship and reduce the future skilled-worker pipeline.", "limitation": "Model predictions, not observed labor dynamics.", "manual_use": "Design exercises that retain comprehension and calibrated independent judgment.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:AUTHOR_INSTITUTIONAL_METADATA_ABSTRACT", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\", \"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Skills formation and teaching", "K:Onboarding and developer fluency", "K:Employment and early-career roles", "K:Remote work and apprenticeship", "K:Economic costs and return" ], "volumes": [ "V06" ] }, { "id": "W120", "label": "Automation, AI, and the Intergenerational Transmission of Knowledge", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Jobs & roles" ], "actual": [ "C:C12" ], "mapped": [ "C:C07", "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Automation changes expert-novice collaboration and may weaken practical knowledge transfer across cohorts.", "limitation": "Abstract assumptions require organizational testing.", "url": "https://arxiv.org/abs/2507.16078", "authors": "Ide", "year": "2026", "attributes": { "label": "Automation, AI, and the Intergenerational Transmission of Knowledge", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Ide", "source": "https://arxiv.org/abs/2507.16078", "contribution": "Automation changes expert-novice collaboration and may weaken practical knowledge transfer across cohorts.", "limitation": "Abstract assumptions require organizational testing.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Theoretical OLG task model (not empirical labor data)", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2507.16078", "publication_status_note": "Theoretical model of intergenerational knowledge transmission", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass2_source_locator": "https://arxiv.org/html/2507.16078", "pass2_source_version": "arXiv HTML banner v9 2026-06-08; body 2026-08-24", "pass2_inspection_scope": "Abstract and task-learning OLG model mechanism and appendix headings; frozen PDF-date check pending", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NOT_APPLICABLE", "pass2_research_design": "Theoretical task-based overlapping-generations tacit knowledge diffusion", "pass2_critical_limitation": "Conditional theoretical results not empirical skill or employment impacts; inconsistent date across HTML/banner", "pass2_audit_date": "2026-10-10", "pass5_audit_date": "2026-10-10", "pass5_version": "arXiv:2507.16078v1 PDF July 2025 versus v9 PDF June 2026; same-version HTML date Aug 2026 mismatch", "pass5_primary_locator": "https://arxiv.org/pdf/2507.16078v1 ; https://arxiv.org/pdf/2507.16078v9", "pass5_inspection_depth": "PRIMARY_VERSIONED_PDFS_INTRO_AND_CURRENT_MODEL_PROPOSITION_4_EQUATION_11", "pass5_page_scope": "v1 PDF p.1; v9 PDF pp.1-4 and pp.25-27 (Eq.11, Prop.4, Figure3); v9 HTML banner date checked", "pass5_sample": "Mathematical overlapping-generation theory, no empirical software-team sample", "pass5_main_finding": "v1 has 0.05-0.35 pp projected growth-loss scenarios; v9 derives learning composition mechanism even with full novice employment, and an immediate-positive/long-run-negative output ratio under stated parameters. Equation (11) independently recomputed at Figure3 parameters.", "pass5_residual_limitation": "No empirical data or observed human developer retention; HTML v9 displays Aug 24 2026 although v9 PDF cover is June 9, 2026; rendered source date inconsistency remains.", "pass5_original_data_replicated": "NO", "pass5_provenance": "PASS5_2026-10-10_SCOPED_PRIMARY_AND_VERSIONED_ABSTRACT", "pass6_date": "2026-10-10", "pass6_locator": "https://arxiv.org/abs/2507.16078", "pass6_inspection_depth": "ARXIV_HISTORY_V9_PDF_V9_EXPERIMENTAL_HTML", "pass6_page_scope": "arxiv history line34, v9 PDF p0, HTML lines70 and 1087", "pass6_finding": "v9 upload June 8; PDF cover June 9; experimental HTML internal August24", "pass6_limitation": "HTML_TRANSFORMATION_DATE_CAUSE_UNKNOWN", "pass6_original_data_replicated": "NO", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Agent failure and escalation", "K:Skills formation and teaching", "K:Employment and early-career roles", "K:Remote work and apprenticeship", "K:Economic costs and return", "K:Evaluation methodology and baselines", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W121", "label": "Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C07", "C:C10", "C:C11" ], "printed": true, "summary": "Cognitive offloading changes measures of engagement and recall, a possible analogy for programming learning.", "limitation": "Essay writing rather than code; causality and interpretation contested.", "url": "https://arxiv.org/abs/2506.08872", "authors": "Kosmyna", "year": "2025", "attributes": { "label": "Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task", "kind": "paper", "group": "Skills & learning", "year": "2025", "lead_author": "Kosmyna", "source": "https://arxiv.org/abs/2506.08872", "contribution": "Cognitive offloading changes measures of engagement and recall, a possible analogy for programming learning.", "limitation": "Essay writing rather than code; causality and interpretation contested.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "Essay-writing EEG, not programming experiment", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2506.08872", "publication_status_note": "Essay writing experiment, not software developer retention trial", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Independent verification and oracles", "K:Human cognitive load", "K:Skills formation and teaching", "K:Cognitive offloading and skill debt", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W122", "label": "AI Didn't Make Programming Easier. It Just Made It Differently Difficult", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Skills & learning", "T:Verification & review" ], "actual": [ "C:C01" ], "mapped": [ "C:C01", "C:C08", "C:C10", "C:C11" ], "printed": true, "summary": "AI relocates effort from syntax construction to mental models, judgment, decomposition and integration.", "limitation": "Thought piece, not a measured trend.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-skills-learning", "authors": "Osborn", "year": "2026", "attributes": { "label": "AI Didn't Make Programming Easier. It Just Made It Differently Difficult", "kind": "paper", "group": "Skills & learning", "year": "2026", "lead_author": "Osborn", "source": "https://www.sepolimi.com/p/se-ai-bibliography-skills-learning", "contribution": "AI relocates effort from syntax construction to mental models, judgment, decomposition and integration.", "limitation": "Thought piece, not a measured trend.", "manual_use": "Design exercises that retain comprehension and calibrated independent judgment.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C01\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W123", "label": "Firms' GitHub Copilot Adoption and Labor Market Outcomes for Software Engineers", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [ "C:C12" ], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Early adopter firms show higher software hiring, especially junior hiring, contradicting simple substitution stories.", "limitation": "Firm adoption selection and platform measures complicate causal attribution.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "authors": "Baird", "year": "2026", "attributes": { "label": "Firms' GitHub Copilot Adoption and Labor Market Outcomes for Software Engineers", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Baird", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "Early adopter firms show higher software hiring, especially junior hiring, contradicting simple substitution stories.", "limitation": "Firm adoption selection and platform measures complicate causal attribution.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W124", "label": "Artificial Intelligence, Productivity, and the Workforce: Evidence from Corporate Executives", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C02", "C:C11", "C:C12" ], "printed": true, "summary": "Leaders anticipate augmentation and work redesign, creating a comparison between aspirations and observed labor data.", "limitation": "Plans and opinions not realized employment.", "url": "https://www.nber.org/papers/w34984", "authors": "Baslandze", "year": "2026", "attributes": { "label": "Artificial Intelligence, Productivity, and the Workforce: Evidence from Corporate Executives", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Baslandze", "source": "https://www.nber.org/papers/w34984", "contribution": "Leaders anticipate augmentation and work redesign, creating a comparison between aspirations and observed labor data.", "limitation": "Plans and opinions not realized employment.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://www.nber.org/papers/w34984", "pass7_identity_source_class": "institutional_working_paper", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W125", "label": "Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of Artificial Intelligence", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Young workers in AI-exposed occupations show relative employment declines in US administrative data.", "limitation": "Exposure and employment shifts do not uniquely identify AI causation.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "authors": "Brynjolfsson", "year": "2026", "attributes": { "label": "Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of Artificial Intelligence", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Brynjolfsson", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "Young workers in AI-exposed occupations show relative employment declines in US administrative data.", "limitation": "Exposure and employment shifts do not uniquely identify AI causation.", "manual_use": "Distinguish hiring composition, worker outcomes and causal attribution.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W126", "label": "How Does AI Change Labor Demand? Evidence from 41 Countries", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "AI adopters change experience requirements toward senior roles across multiple countries.", "limitation": "Vacancy wording and changes do not equal actual net employment.", "url": "https://digitaleconomy.stanford.edu/publication/how-does-ai-change-labor-demand/", "authors": "Chandar", "year": "2026", "attributes": { "label": "How Does AI Change Labor Demand? Evidence from 41 Countries", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Chandar", "source": "https://digitaleconomy.stanford.edu/publication/how-does-ai-change-labor-demand/", "contribution": "AI adopters change experience requirements toward senior roles across multiple countries.", "limitation": "Vacancy wording and changes do not equal actual net employment.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://digitaleconomy.stanford.edu/publication/how-does-ai-change-labor-demand/", "publication_status_note": "Cross-country labor demand; job posting and hiring are distinct from employment", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_PAPER_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Stanford Digital Economy Lab publication landing record; methods and original microdata not independently audited", "endpoint_boundary": "Job postings/hiring and labor demand in 41 countries; neither a measure of software output nor a universal employment effect.", "pass2_source_locator": "https://digitaleconomy.stanford.edu/app/uploads/2026/09/HowDoesAIChangeLaborDemand.pdf", "pass2_source_version": "September 2026 primary 156-page paper", "pass2_inspection_scope": "Abstract pp 2-3 Sections 4-5 and Figure 3 printed pp 27-28", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Instrumented matched foreign multinational affiliate adoption/event study", "pass2_critical_limitation": "Junior share is not junior headcount; observed treatment via AI job-posting proxy and exclusion restrictions", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W127", "label": "Remote Work Leaves Younger Workers Sidelined", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C09", "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Remote working may impair early-career access and mentorship and confound post-2022 AI hiring interpretations.", "limitation": "Remote work and AI adoption overlap; country context matters.", "url": "https://libertystreeteconomics.newyorkfed.org/2026/06/remote-work-leaves-younger-workers-sidelined/", "authors": "Emanuel", "year": "2026", "attributes": { "label": "Remote Work Leaves Younger Workers Sidelined", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Emanuel", "source": "https://libertystreeteconomics.newyorkfed.org/2026/06/remote-work-leaves-younger-workers-sidelined/", "contribution": "Remote working may impair early-career access and mentorship and confound post-2022 AI hiring interpretations.", "limitation": "Remote work and AI adoption overlap; country context matters.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://libertystreeteconomics.newyorkfed.org/2026/06/remote-work-leaves-younger-workers-sidelined/", "pass7_identity_source_class": "institutional_primary_commentary", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Agent context and persistent memory", "K:Employment and early-career roles", "K:Remote work and apprenticeship" ], "volumes": [] }, { "id": "W128", "label": "Labor Market Consequences of Generative AI: Early Evidence from Norway", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Early Norwegian data do not reveal the strong job losses predicted by some US exposure analyses.", "limitation": "Follow-up window and adoption rates may differ.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "authors": "Facius", "year": "2026", "attributes": { "label": "Labor Market Consequences of Generative AI: Early Evidence from Norway", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Facius", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "Early Norwegian data do not reveal the strong job losses predicted by some US exposure analyses.", "limitation": "Follow-up window and adoption rates may differ.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Employment and early-career roles" ], "volumes": [ "V06" ] }, { "id": "W129", "label": "AI Has Not Impacted the Youth Labor Market in Finland", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Finnish youth workforce data show no detectable AI-induced collapse in the observed horizon.", "limitation": "Non-detection is not proof of zero long-term effects.", "url": "https://www.etla.fi/en/publications/working-papers-en/ai-has-not-impacted-the-youth-labor-market-in-finland/", "authors": "Kauhanen", "year": "2026", "attributes": { "label": "AI Has Not Impacted the Youth Labor Market in Finland", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Kauhanen", "source": "https://www.etla.fi/en/publications/working-papers-en/ai-has-not-impacted-the-youth-labor-market-in-finland/", "contribution": "Finnish youth workforce data show no detectable AI-induced collapse in the observed horizon.", "limitation": "Non-detection is not proof of zero long-term effects.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://www.etla.fi/en/publications/working-papers-en/ai-has-not-impacted-the-youth-labor-market-in-finland/", "publication_status_note": "Finnish labor evidence cannot automatically generalize internationally", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_PAPER_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "pass2_source_locator": "https://www.etla.fi/wp-content/uploads/ETLA-Working-Papers-135.pdf", "pass2_source_version": "ETLA Working Papers 135 January 2026", "pass2_inspection_scope": "Original figures 3 7 8 and methods and conclusions printed pp 10 15 16 18", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Registry headcounts and exposure quantile descriptive plus firm fixed effect contrasts", "pass2_critical_limitation": "No controlled experiment assigning chatbot use; negative detectable exposure gradient not proof no AI effect", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles" ], "volumes": [ "V06" ] }, { "id": "W130", "label": "A New Look at AI's Impact on Jobs: Firm-Level AI Spending and Workforce Adjustment", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "High AI spending correlates with growing firm employment including entry hires.", "limitation": "Surviving growth firms and spending are endogenous.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "authors": "Kharazian", "year": "2026", "attributes": { "label": "A New Look at AI's Impact on Jobs: Firm-Level AI Spending and Workforce Adjustment", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Kharazian", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "High AI spending correlates with growing firm employment including entry hires.", "limitation": "Surviving growth firms and spending are endogenous.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W131", "label": "The Broken Ladder: AI, Remote Work, and Early-Career Hiring", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C04", "C:C11", "C:C12" ], "printed": true, "summary": "Junior hiring contraction may be more closely explained by remote-work effects than AI deployment alone.", "limitation": "Attribution depends on exposure and comparator specification.", "url": "https://wrap.warwick.ac.uk/id/eprint/202349/", "authors": "Lambert", "year": "2026", "attributes": { "label": "The Broken Ladder: AI, Remote Work, and Early-Career Hiring", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Lambert", "source": "https://wrap.warwick.ac.uk/id/eprint/202349/", "contribution": "Junior hiring contraction may be more closely explained by remote-work effects than AI deployment alone.", "limitation": "Attribution depends on exposure and comparator specification.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_pass2_section_scoped", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://wrap.warwick.ac.uk/id/eprint/202349/", "publication_status_note": "Junior hiring and job ads; controls for WFH alter significance; confirm actual version before quoting numbers", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_INSTITUTION_PAPER_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "pass2_source_locator": "https://cep.lse.ac.uk/pubs/download/dp2193.pdf", "pass2_source_version": "LSE CEP Discussion Paper 2193 June 2026 primary 83-page PDF", "pass2_inspection_scope": "Abstract plus original identification printed around pp 12-13 and joint treatment caution", "pass2_methods_status": "PRIMARY_MANUSCRIPT_METHODS_AND_TABLES_SELECTED", "pass2_replication_status": "NO", "pass2_research_design": "Observational continuous-exposure difference in differences with WFH co-treatment controls", "pass2_critical_limitation": "AI and WFH exposure rank correlation 0.77 and strong parallel exposure trend conditions; remote work not randomized", "pass2_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Specifications and governance", "K:Employment and early-career roles", "K:Remote work and apprenticeship" ], "volumes": [ "V06" ] }, { "id": "W132", "label": "New Jobs in 140 Years of Data: Why the AI Displacement Fear Is Overstated — and What to Worry About Instead", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [], "mapped": [ "C:C06", "C:C09", "C:C11", "C:C12" ], "printed": true, "summary": "Historical occupational turnover suggests task change and adaptation alongside displacement risk.", "limitation": "Long historical analogies may not hold at current AI speed.", "url": "https://cepr.org/voxeu/columns/new-jobs-140-years-data-why-ai-displacement-fear-overstated-and-what-worry-about", "authors": "Skoglund", "year": "2026", "attributes": { "label": "New Jobs in 140 Years of Data: Why the AI Displacement Fear Is Overstated — and What to Worry About Instead", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Skoglund", "source": "https://cepr.org/voxeu/columns/new-jobs-140-years-data-why-ai-displacement-fear-overstated-and-what-worry-about", "contribution": "Historical occupational turnover suggests task change and adaptation alongside displacement risk.", "limitation": "Long historical analogies may not hold at current AI speed.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://cepr.org/voxeu/columns/new-jobs-140-years-data-why-ai-displacement-fear-overstated-and-what-worry-about", "pass7_identity_source_class": "author_primary_analysis", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Vulnerability and secure code", "K:Ownership and knowledge transfer", "K:Employment and early-career roles", "K:Long-running agent execution" ], "volumes": [] }, { "id": "W133", "label": "Firm Data on AI", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Most companies currently report no major AI-driven employment changes, while future staffing expectations modestly decline.", "limitation": "Self-report and delayed effects; broad not SWE-specific.", "url": "https://www.nber.org/papers/w34836", "authors": "Yotzov", "year": "2026", "attributes": { "label": "Firm Data on AI", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Yotzov", "source": "https://www.nber.org/papers/w34836", "contribution": "Most companies currently report no major AI-driven employment changes, while future staffing expectations modestly decline.", "limitation": "Self-report and delayed effects; broad not SWE-specific.", "manual_use": "Distinguish hiring composition, worker outcomes and causal attribution.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://www.nber.org/papers/w34836", "pass7_identity_source_class": "institutional_working_paper", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W134", "label": "Artificial Intelligence and the Labor Market", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "AI-exposed roles can see pay pressure even when headcount and occupation effects differ.", "limitation": "Reported wage effect excludes SW engineering roles, limiting manual applicability.", "url": "https://www.nber.org/papers/w33509", "authors": "Hampole", "year": "2025", "attributes": { "label": "Artificial Intelligence and the Labor Market", "kind": "paper", "group": "Jobs & roles", "year": "2025", "lead_author": "Hampole", "source": "https://www.nber.org/papers/w33509", "contribution": "AI-exposed roles can see pay pressure even when headcount and occupation effects differ.", "limitation": "Reported wage effect excludes SW engineering roles, limiting manual applicability.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://www.nber.org/papers/w33509", "pass7_identity_source_class": "institutional_working_paper", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W135", "label": "Generative AI as Seniority-Biased Technological Change: Evidence from U.S. Résumé and Job Posting Data", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "AI adoption may shift demand toward experienced software workers at the expense of junior vacancies.", "limitation": "Job-posting measurement and selection bias.", "url": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5425555", "authors": "Hosseini", "year": "2025", "attributes": { "label": "Generative AI as Seniority-Biased Technological Change: Evidence from U.S. Résumé and Job Posting Data", "kind": "paper", "group": "Jobs & roles", "year": "2025", "lead_author": "Hosseini", "source": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5425555", "contribution": "AI adoption may shift demand toward experienced software workers at the expense of junior vacancies.", "limitation": "Job-posting measurement and selection bias.", "manual_use": "Use to build a reviewer-calibration exercise with injected wrong suggestions and measured detection rates.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5425555", "pass7_identity_source_class": "primary_versioned_manuscript", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Human cognitive load", "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [ "V05" ] }, { "id": "W136", "label": "Still Waters, Rapid Currents: Early Labor Market Transformation under Generative AI", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C09", "C:C11", "C:C12" ], "printed": true, "summary": "No material early change in worker earnings or hours despite adoption; workplace tasks can shift first.", "limitation": "Early interval, labor market protections and country context.", "url": "https://www.nber.org/papers/w33777", "authors": "Humlum", "year": "2025", "attributes": { "label": "Still Waters, Rapid Currents: Early Labor Market Transformation under Generative AI", "kind": "paper", "group": "Jobs & roles", "year": "2025", "lead_author": "Humlum", "source": "https://www.nber.org/papers/w33777", "contribution": "No material early change in worker earnings or hours despite adoption; workplace tasks can shift first.", "limitation": "Early interval, labor market protections and country context.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_institutional_record_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://www.nber.org/papers/w33777", "publication_status_note": "Denmark administrative earnings/hours; not universally comparable to hiring postings", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "WORKING_PAPER_INSTITUTION", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "pass2_source_locator": "https://www.nber.org/papers/w33777", "pass2_source_version": "NBER WP33777 original May 2025 and institutional March 2026 revision", "pass2_inspection_scope": "Original institutional publication summary for revision; full numerical tables not independently inspected", "pass2_methods_status": "PRIMARY_INSTITUTIONAL_RECORD_ONLY", "pass2_replication_status": "NO", "pass2_research_design": "Linked Danish chatbot-use surveys and wage/hour employment records", "pass2_critical_limitation": "Full PDF coefficient scale and identification not checked; cannot infer universal or long-run zero impact", "pass2_audit_date": "2026-10-10", "pass5_audit_date": "2026-10-10", "pass5_version": "RFBerlin Discussion Paper 078/26, original PDF 13 March 2026; NBER revision March 2026", "pass5_primary_locator": "https://www.rfberlin.com/wp-content/uploads/2026/03/26078.pdf", "pass5_inspection_depth": "ORIGINAL_132_PAGE_PDF_DESIGN_EQUATIONS_FIGURES_AND_SELECTED_RESULTS", "pass5_page_scope": "PDF pp.3-7, 15-16, 20-26, 29-31; printed pp.1-5, 13-14, 18-24, 27-29", "pass5_sample": "Approx 25,000 workers / 7,000 workplaces, 11 exposed occupations, linked to administrative Danish data through Dec 2024", "pass5_main_finding": "Eq(3) OLS pooled DiD with worker-specific linear trends and workplace-occupation clustered SE; Figure 5 dynamic CIs exclude >3% earnings shifts; pooled Figure 7 excludes >2%; survey adoption/descriptive differences should not be causalized.", "pass5_residual_limitation": "Primary tables beyond selected figures not exhaustively inspected; Statistics Denmark linked raw data unavailable for independent regression.", "pass5_original_data_replicated": "NO", "pass5_provenance": "PASS5_2026-10-10_SCOPED_PRIMARY_AND_VERSIONED_ABSTRACT", "pass6_date": "2026-10-10", "pass6_locator": "https://www.rfberlin.com/wp-content/uploads/2026/03/26078.pdf", "pass6_inspection_depth": "PRIMARY_132_PAGE_PDF_METHODS_AND_FIGURE_TEXT", "pass6_page_scope": "PDF p24-25; printed p22-23", "pass6_finding": "Eq2 dynamic/eq3 pooled; 9/4% pre-adoption earnings premiums; 3/2% different confidence intervals", "pass6_limitation": "LICENSED_DENMARK_MICRODATA_UNAVAILABLE", "pass6_original_data_replicated": "NO", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Agent context and persistent memory", "K:Employment and early-career roles" ], "volumes": [ "V06", "V05" ] }, { "id": "W137", "label": "The Labor Market Is Tilting Toward Seniority", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Posted development vacancies disproportionately target seniority compared with entry-level roles.", "limitation": "Descriptive share changes cannot attribute cause to AI.", "url": "https://hiringlab.indeed.com/2026/07/23/the-labor-market-is-tilting-toward-seniority/", "authors": "Aidala", "year": "2026", "attributes": { "label": "The Labor Market Is Tilting Toward Seniority", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Aidala", "source": "https://hiringlab.indeed.com/2026/07/23/the-labor-market-is-tilting-toward-seniority/", "contribution": "Posted development vacancies disproportionately target seniority compared with entry-level roles.", "limitation": "Descriptive share changes cannot attribute cause to AI.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://hiringlab.indeed.com/2026/07/23/the-labor-market-is-tilting-toward-seniority/", "pass7_identity_source_class": "producer_primary_report", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W138", "label": "AI's Impact on Labor and Hiring", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [], "mapped": [ "C:C04", "C:C11", "C:C12" ], "printed": true, "summary": "Employers may adjust planned recruiting before adjusting existing headcount.", "limitation": "Reports intent and sentiment rather than realized effects.", "url": "https://libertystreeteconomics.newyorkfed.org/2026/08/ais-impact-on-labor-and-hiring/", "authors": "Athreya", "year": "2026", "attributes": { "label": "AI's Impact on Labor and Hiring", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Athreya", "source": "https://libertystreeteconomics.newyorkfed.org/2026/08/ais-impact-on-labor-and-hiring/", "contribution": "Employers may adjust planned recruiting before adjusting existing headcount.", "limitation": "Reports intent and sentiment rather than realized effects.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://libertystreeteconomics.newyorkfed.org/2026/08/ais-impact-on-labor-and-hiring/", "pass7_identity_source_class": "institutional_primary_commentary", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Specifications and governance", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W139", "label": "Do Job Postings Show Early Labor-Market Effects of AI?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [ "C:C12" ], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Software vacancy decline predates widespread ChatGPT use in some US data, weakening simplistic causal narratives.", "limitation": "Vacancy data are incomplete and other economic shocks matter.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "authors": "Audoly", "year": "2026", "attributes": { "label": "Do Job Postings Show Early Labor-Market Effects of AI?", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Audoly", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "Software vacancy decline predates widespread ChatGPT use in some US data, weakening simplistic causal narratives.", "limitation": "Vacancy data are incomplete and other economic shocks matter.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Employment and early-career roles", "K:Economic costs and return" ], "volumes": [ "V06" ] }, { "id": "W140", "label": "AI and Job Postings: From Destruction to Creation?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [ "C:C12" ], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Some developer vacancies rise after new coding agent capabilities become available.", "limitation": "Product release timing is not randomized AI exposure.", "url": "https://hiringlab.indeed.com/2026/07/08/ai-and-job-postings-from-destruction-to-creation/", "authors": "Gallacher", "year": "2026", "attributes": { "label": "AI and Job Postings: From Destruction to Creation?", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Gallacher", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "Some developer vacancies rise after new coding agent capabilities become available.", "limitation": "Product release timing is not randomized AI exposure.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Controlled human or field experiment", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Controlled human or field experiment", "reviewed_evidence_class": "Observational job-postings trend analysis (not a randomized field experiment)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "2026", "publication_source_url": "https://hiringlab.indeed.com/2026/07/08/ai-and-job-postings-from-destruction-to-creation/", "publication_status_note": "Indeed Hiring Lab observational commentary", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Employment and early-career roles" ], "volumes": [ "V06" ] }, { "id": "W141", "label": "Google's AI & Economy ATLAS v1.0: Mapping Gemini Usage in the Economy", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Maps adoption by tasks; tool usage does not directly imply task replacement or labor demand change.", "limitation": "One provider and incomplete agent usage coverage.", "url": "https://arxiv.org/abs/2608.00038", "authors": "Iscenko", "year": "2026", "attributes": { "label": "Google's AI & Economy ATLAS v1.0: Mapping Gemini Usage in the Economy", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Iscenko", "source": "https://arxiv.org/abs/2608.00038", "contribution": "Maps adoption by tasks; tool usage does not directly imply task replacement or labor demand change.", "limitation": "One provider and incomplete agent usage coverage.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://arxiv.org/abs/2608.00038", "pass7_identity_source_class": "author_preprint", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W142", "label": "AI Is Probably Not (Yet) the Reason for Labor Market Weakening", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Economics" ], "actual": [ "C:C12" ], "mapped": [ "C:C03", "C:C11", "C:C12" ], "printed": true, "summary": "Alternative US estimation fails to identify significant net AI-driven labor weakening.", "limitation": "Method and observation window could miss subgroup impacts.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "authors": "Nunn", "year": "2026", "attributes": { "label": "AI Is Probably Not (Yet) the Reason for Labor Market Weakening", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "Nunn", "source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "contribution": "Alternative US estimation fails to identify significant net AI-driven labor weakening.", "limitation": "Method and observation window could miss subgroup impacts.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Agent failure and escalation", "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W143", "label": "New data show no AI jobs apocalypse — for now", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles" ], "actual": [], "mapped": [ "C:C11", "C:C12" ], "printed": true, "summary": "Aggregate labor indicators remain more stable than narratives of immediate massive AI displacement.", "limitation": "Aggregate trends can mask cohort, wage and industry effects.", "url": "https://www.brookings.edu/articles/new-data-show-no-ai-jobs-apocalypse-for-now/", "authors": "Kinder", "year": "2025", "attributes": { "label": "New data show no AI jobs apocalypse — for now", "kind": "paper", "group": "Jobs & roles", "year": "2025", "lead_author": "Kinder", "source": "https://www.brookings.edu/articles/new-data-show-no-ai-jobs-apocalypse-for-now/", "contribution": "Aggregate labor indicators remain more stable than narratives of immediate massive AI displacement.", "limitation": "Aggregate trends can mask cohort, wage and industry effects.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://www.brookings.edu/articles/new-data-show-no-ai-jobs-apocalypse-for-now/", "pass7_identity_source_class": "institutional_primary_commentary", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Employment and early-career roles", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W144", "label": "2026 Global AI Jobs Barometer: Two futures for jobs in an AI era", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Jobs & roles", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Rapidly changing skill demands and experience requirements may reshape developer career ladders.", "limitation": "Vendor interpretation and task-exposure proxies; not causal.", "url": "https://www.pwc.com/gx/en/issues/artificial-intelligence/publications/artificial-intelligence-study.html", "authors": "PwC", "year": "2026", "attributes": { "label": "2026 Global AI Jobs Barometer: Two futures for jobs in an AI era", "kind": "paper", "group": "Jobs & roles", "year": "2026", "lead_author": "PwC", "source": "https://www.pwc.com/gx/en/issues/artificial-intelligence/publications/artificial-intelligence-study.html", "contribution": "Rapidly changing skill demands and experience requirements may reshape developer career ladders.", "limitation": "Vendor interpretation and task-exposure proxies; not causal.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://www.pwc.com/gx/en/issues/artificial-intelligence/publications/artificial-intelligence-study.html", "pass7_identity_source_class": "producer_primary_report", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-jobs-roles", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Skills formation and teaching", "K:Employment and early-career roles" ], "volumes": [] }, { "id": "W145", "label": "ROI of AI-Assisted Software Development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Economics", "T:Productivity" ], "actual": [ "C:C12" ], "mapped": [ "C:C02", "C:C10", "C:C11", "C:C12" ], "printed": true, "summary": "Offers a cross-functional return-on-investment framework for AI-assisted delivery beyond raw code productivity.", "limitation": "ROI 39% and eight-month payback are scenarios/model outputs, not measured experimental financial returns.", "url": "https://dora.dev/ai/roi/report/", "authors": "DORA", "year": "2026", "attributes": { "label": "ROI of AI-Assisted Software Development", "kind": "paper", "group": "Economics", "year": "2026", "lead_author": "DORA", "source": "https://www.sepolimi.com/p/se-ai-bibliography-economics", "contribution": "Offers a cross-functional return-on-investment framework for AI-assisted delivery beyond raw code productivity.", "limitation": "ROI 39% and eight-month payback are scenarios/model outputs, not measured experimental financial returns.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Practitioner guidance / ROI calculator (not an experimental study)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "2026", "publication_source_url": "https://dora.dev/ai/roi/report/", "publication_status_note": "DORA practitioner ROI framework/report", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C12\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Human cognitive load", "K:Economic costs and return", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W146", "label": "McKinsey Technology Trends Outlook 2026", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Economics", "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C02", "C:C06", "C:C09", "C:C11", "C:C12" ], "printed": true, "summary": "Positions legacy system context and secure deployment as adoption constraints, and stresses both acceleration and uneven results.", "limitation": "Survey opinions and mixed trend indicators are not causal SWE productivity measures.", "url": "https://www.mckinsey.com/capabilities/tech-and-ai/our-insights/the-top-trends-in-tech", "authors": "Chui", "year": "2026", "attributes": { "label": "McKinsey Technology Trends Outlook 2026", "kind": "paper", "group": "Economics", "year": "2026", "lead_author": "Chui", "source": "https://www.mckinsey.com/capabilities/tech-and-ai/our-insights/the-top-trends-in-tech", "contribution": "Positions legacy system context and secure deployment as adoption constraints, and stresses both acceleration and uneven results.", "limitation": "Survey opinions and mixed trend indicators are not causal SWE productivity measures.", "manual_use": "Translate into a context-handoff pattern separating working context, durable facts and verified system knowledge.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://www.mckinsey.com/capabilities/tech-and-ai/our-insights/the-top-trends-in-tech", "pass7_identity_source_class": "producer_primary_report", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-economics", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Controlled productivity evidence", "K:Developer workflow and adoption", "K:Vulnerability and secure code", "K:System understanding and rationale", "K:Agent context and persistent memory", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W147", "label": "To Ban or not to Ban? How Open Source Projects Govern GenAI Contributions", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure", "T:Verification & review" ], "actual": [ "C:C11" ], "mapped": [ "C:C04", "C:C08", "C:C11", "C:C12" ], "printed": true, "summary": "Projects adopt distinct governance stances to regulate low-cost agent PR supply and scarce maintainer review capacity.", "limitation": "Strategy taxonomy does not establish effectiveness.", "url": "https://arxiv.org/abs/2603.26487", "authors": "Yang", "year": "2026", "attributes": { "label": "To Ban or not to Ban? How Open Source Projects Govern GenAI Contributions", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Yang", "source": "https://arxiv.org/abs/2603.26487", "contribution": "Projects adopt distinct governance stances to regulate low-cost agent PR supply and scarce maintainer review capacity.", "limitation": "Strategy taxonomy does not establish effectiveness.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH11:ORIGINAL_PDF_METHODS_AND_TABLES", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Specifications and governance", "K:Economic costs and return", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W148", "label": "SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure", "T:What agents can do" ], "actual": [ "C:C04", "C:C07", "C:C11" ], "mapped": [ "C:C03", "C:C04", "C:C07", "C:C11" ], "printed": true, "summary": "Process discipline can improve generated code on selected functional tests compared with unconstrained runs.", "limitation": "Small benchmark and GPT-3.5-era setup; process emulation not production governance.", "url": "https://doi.org/10.1109/ICSE55347.2025.00140", "authors": "Lin", "year": "2026", "attributes": { "label": "SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Lin", "source": "https://www.sepolimi.com/p/se-ai-bibliography-engineering-structure", "contribution": "Process discipline can improve generated code on selected functional tests compared with unconstrained runs.", "limitation": "Small benchmark and GPT-3.5-era setup; process emulation not production governance.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "HumanEval/MBPP coding benchmarks, not live agile field study", "publication_year_from_independent_source": "2025", "publication_source_url": "https://doi.org/10.1109/ICSE55347.2025.00140", "publication_status_note": "ICSE 2025 (arXiv manuscript first posted 2024)", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:PUBLISHER_ABSTRACT_ONLY; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://arxiv.org/pdf/2403.15852", "pass4_audit_version": "Original 14-page arXiv:2403.15852v2 author manuscript, 2024-10-31; 2025 IEEE conference record separately checked", "pass4_audit_depth": "AUTHOR_PREPRINT_PDF_METHODS_TABLES_II_III_PAGE_INSPECTED", "pass4_audit_methods_locators": "Author manuscript PDF pp. 6-7, Table II and Table III, experiment GPT-3.5 and five repeats; benchmark MBPP-582 test anomaly", "pass4_audit_sample": "164 HumanEval problems; 427 MBPP problems; HumanEval-ET/MBPP-ET extended test sets; five GPT-3.5 runs with T=0.8", "pass4_audit_observation": "Mean pass@1 Scrum 75.2/65.5/82.5/56.7; Table II baseline 64.4/49.8/77.5/53.9; MBPP-582 mismatched test input shown in Listing 1", "pass4_audit_boundary": "Final ICSE PDF tables not compared with author v2; reported p-values not recomputed from run-level outputs; no human team rollout evidence", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C04\", \"C:C07\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Architecture and modularity", "K:Specifications and governance" ], "volumes": [ "V06" ] }, { "id": "W149", "label": "Making AI Visible, Not Vanished: How AI Policies Reshape Developer Experience on GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure", "T:Code quality & security" ], "actual": [ "C:C11" ], "mapped": [ "C:C04", "C:C05", "C:C11" ], "printed": true, "summary": "Explicit project policies correlate with fewer measured code smells and richer human PR discussion without suppressing AI use.", "limitation": "Eight-week matched window cannot rule out proactive-maintainer selection.", "url": "https://arxiv.org/abs/2608.03329", "authors": "Chen", "year": "2026", "attributes": { "label": "Making AI Visible, Not Vanished: How AI Policies Reshape Developer Experience on GitHub", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Chen", "source": "https://arxiv.org/abs/2608.03329", "contribution": "Explicit project policies correlate with fewer measured code smells and richer human PR discussion without suppressing AI use.", "limitation": "Eight-week matched window cannot rule out proactive-maintainer selection.", "manual_use": "Make policy, responsibility and bounded workflow executable.", "evidence_class": "Quasi-experimental / matched observation", "editorial_priority": "A", "bibliography_year": "2026", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "Quasi-experimental / matched observation", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING; CH11:ORIGINAL_PDF_METHODS_AND_TABLES", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Technical debt and complexity", "K:Specifications and governance", "K:Evaluation methodology and baselines", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W150", "label": "We Permit the Use of AI, but [...]: The Landscape of AI Policies in Popular Open Source Projects", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure", "T:Code quality & security" ], "actual": [ "C:C04", "C:C07", "C:C11" ], "mapped": [ "C:C01", "C:C04", "C:C05", "C:C07", "C:C11" ], "printed": true, "summary": "Most policies allow AI while specifying disclosure and human responsibility, suggesting workable rather than absolutist governance.", "limitation": "Classifies rules but does not measure their safety effect.", "url": "https://arxiv.org/abs/2609.07542", "authors": "Hora", "year": "2026", "attributes": { "label": "We Permit the Use of AI, but [...]: The Landscape of AI Policies in Popular Open Source Projects", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Hora", "source": "https://arxiv.org/abs/2609.07542", "contribution": "Most policies allow AI while specifying disclosure and human responsibility, suggesting workable rather than absolutist governance.", "limitation": "Classifies rules but does not measure their safety effect.", "manual_use": "Make policy, responsibility and bounded workflow executable.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH07:FULLTEXT_HTML; CH11:ORIGINAL_PDF_METHODS_AND_TABLES", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://arxiv.org/html/2609.07542", "pass4_audit_version": "arXiv:2609.07542v1 (2026-09-07)", "pass4_audit_depth": "ORIGINAL_HTML_METHODS_AND_TABLES_SELECTED", "pass4_audit_methods_locators": "Methods Sections 2.2-2.4; RQ1 Table 1; RQ2 Fig 4; limitations", "pass4_audit_sample": "281 purposively selected policies (245/2000 popular repos + 36 added); 92 dedicated policy files", "pass4_audit_observation": "150/281 mention disclosure obligation; 137/281 require disclosure; 180 double-coded labels, 162 agree", "pass4_audit_boundary": "Selection and coder agreement do not measure policy effectiveness; 118-policy earlier sample not independent", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "pass9_scope": "original HTML cited Zenodo DOI located, unadjusted coder agreement, no source-record download", "ndse2_actual_chapters_json": "[\"C:C04\", \"C:C07\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Specifications and governance", "K:Evaluation methodology and baselines", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W151", "label": "Blueprint First, Model Second: A Framework for Deterministic LLM Workflow", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure", "T:What agents can do" ], "actual": [ "C:C03", "C:C04", "C:C07", "C:C11" ], "mapped": [ "C:C03", "C:C04", "C:C07", "C:C11" ], "printed": true, "summary": "Predefined action blueprints can constrain agent behavior and outperform unrestricted planning on tested workflows.", "limitation": "Domain not typical SWE repositories; benchmark-specific.", "url": "https://arxiv.org/abs/2508.02721", "authors": "Qiu", "year": "2026", "attributes": { "label": "Blueprint First, Model Second: A Framework for Deterministic LLM Workflow", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Qiu", "source": "https://www.sepolimi.com/p/se-ai-bibliography-engineering-structure", "contribution": "Predefined action blueprints can constrain agent behavior and outperform unrestricted planning on tested workflows.", "limitation": "Domain not typical SWE repositories; benchmark-specific.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "Tool/workflow tau-bench, not real coding-team outcomes", "publication_year_from_independent_source": "2025", "publication_source_url": "https://arxiv.org/abs/2508.02721", "publication_status_note": "arXiv preprint (first posted August 2025)", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH07:FULLTEXT_HTML; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass3_audit_primary_url": "https://arxiv.org/html/2508.02721v2", "pass3_audit_version": "arXiv:2508.02721v2 (2026-06-16)", "pass3_audit_depth": "ORIGINAL_HTML_SELECTED_METHODS_AND_TABLES", "pass3_audit_methods_locators": "IV Table I; RQ2 hard constraints; experimental settings", "pass3_audit_sample": "TravelPlanner 1000 tasks; Claude Sonnet 4; three seeds", "pass3_audit_observation": "Final pass 35.56% SCA versus ATLAS 18.00%; hard-constraint macro 38.89 versus 42.00", "pass3_audit_boundary": "Hard constraint outcomes trade off; benchmark does not validate real policy authority", "pass3_audit_original_data_replication": "NO", "pass3_audit_provenance": "PASS3_PRINTED_EDITION_RECONSTRUCTED_2026-10-10", "pass3_audit_date": "2026-10-10", "pass9_scope": "v1/v2 original HTML Table 1/I-II; McNemar from continuous mean not verifiable", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C04\", \"C:C07\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Independent verification and oracles", "K:Benchmarks and construct validity", "K:Architecture and modularity", "K:Specifications and governance", "K:Long-running agent execution" ], "volumes": [ "V06" ] }, { "id": "W152", "label": "Agentic Software Engineering: Foundational Pillars and a Research Roadmap", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure" ], "actual": [ "C:C03", "C:C04", "C:C11" ], "mapped": [ "C:C01", "C:C03", "C:C04", "C:C05", "C:C09", "C:C11", "C:C12" ], "printed": true, "summary": "Provides an architecture for organizing agentic SWE research around dependable processes, collaboration and evaluation.", "limitation": "Roadmap is not evidence of achieved agent reliability.", "url": "https://arxiv.org/abs/2509.06216", "authors": "Hassan", "year": "2026", "attributes": { "label": "Agentic Software Engineering: Foundational Pillars and a Research Roadmap", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Hassan", "source": "https://arxiv.org/abs/2509.06216", "contribution": "Provides an architecture for organizing agentic SWE research around dependable processes, collaboration and evaluation.", "limitation": "Roadmap is not evidence of achieved agent reliability.", "manual_use": "Present as one estimand within a multi-country labor evidence table; avoid deterministic jobs predictions.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2509.06216", "publication_status_note": "Roadmap; initial submission 2025, metadata may reflect 2026 revision", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://arxiv.org/html/2509.06216", "pass4_audit_version": "arXiv:2509.06216v3 (2026-06-24)", "pass4_audit_depth": "ORIGINAL_HTML_CONCEPTUAL_METHOD", "pass4_audit_methods_locators": "Sections 1,4-7 and named proposed artifacts", "pass4_audit_sample": "No intervention cohort; authored roadmap SASE", "pass4_audit_observation": "Four pillars Actors/Processes/Tools/Artifacts; SE4H/SE4A duality; proposed scripts", "pass4_audit_boundary": "Design proposal not validated impact on multi-agent team performance", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C04\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Architecture and modularity", "K:Employment and early-career roles", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W153", "label": "Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:Engineering structure" ], "actual": [ "C:C01", "C:C04", "C:C11" ], "mapped": [ "C:C01", "C:C04", "C:C11", "C:C12" ], "printed": true, "summary": "Expands the scope of agentic SWE to requirements, design, teamwork and organization-wide responsibility.", "limitation": "Framing proposal; no new controlled outcome evidence.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-engineering-structure", "authors": "Hoda", "year": "2026", "attributes": { "label": "Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary", "kind": "paper", "group": "Engineering structure", "year": "2026", "lead_author": "Hoda", "source": "https://www.sepolimi.com/p/se-ai-bibliography-engineering-structure", "contribution": "Expands the scope of agentic SWE to requirements, design, teamwork and organization-wide responsibility.", "limitation": "Framing proposal; no new controlled outcome evidence.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://arxiv.org/html/2510.19692", "pass4_audit_version": "arXiv:2510.19692v2 (2026-02-17)", "pass4_audit_depth": "ORIGINAL_HTML_CONCEPTUAL_METHOD", "pass4_audit_methods_locators": "Abstract, values and vocabulary sections", "pass4_audit_sample": "No original randomized or natural-experiment sample", "pass4_audit_observation": "Advocates lifecycle-wide agentic SE and preliminary CRAFT values", "pass4_audit_boundary": "Normative framework not empirical proof of organizational effects", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C04\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W154", "label": "Comprehension Debt in GenAI-Assisted Software Engineering Projects", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C05", "C:C09", "C:C10" ], "printed": true, "summary": "Delegated code generation may leave developers with latent understanding deficits analogous to accumulated technical debt.", "limitation": "Thematic self-reports from students, without effect-size or objective comprehension baseline.", "url": "https://arxiv.org/abs/2604.13277", "authors": "Ahmad", "year": "2026", "attributes": { "label": "Comprehension Debt in GenAI-Assisted Software Engineering Projects", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Ahmad", "source": "https://arxiv.org/abs/2604.13277", "contribution": "Delegated code generation may leave developers with latent understanding deficits analogous to accumulated technical debt.", "limitation": "Thematic self-reports from students, without effect-size or objective comprehension baseline.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Qualitative student diary study (not commercial self-report)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "2026", "publication_source_url": "https://arxiv.org/abs/2604.13277", "publication_status_note": "Student diary qualitative study (arXiv/EASE 2026)", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING; CH10:ARXIV_PDF_PAGES_VERIFIED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Technical debt and complexity", "K:Human cognitive load", "K:Skills formation and teaching", "K:Cognitive offloading and skill debt", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W155", "label": "ChatGPT: Friend or Foe When Comprehending and Changing Unfamiliar Code", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C09", "C:C10" ], "mapped": [ "C:C07", "C:C09", "C:C10" ], "printed": true, "summary": "ChatGPT may aid completion of changes while developers still devote most time to reconstructing existing-system behavior.", "limitation": "Ten advanced students; results exploratory and not statistically tested.", "url": "https://arxiv.org/abs/2605.10702", "authors": "Anderson", "year": "2026", "attributes": { "label": "ChatGPT: Friend or Foe When Comprehending and Changing Unfamiliar Code", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Anderson", "source": "https://arxiv.org/abs/2605.10702", "contribution": "ChatGPT may aid completion of changes while developers still devote most time to reconstructing existing-system behavior.", "limitation": "Ten advanced students; results exploratory and not statistically tested.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING; CH10:ARXIV_PDF_PAGES_VERIFIED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\", \"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Skills formation and teaching", "K:System understanding and rationale" ], "volumes": [ "V06" ] }, { "id": "W156", "label": "LACY: Simulating Expert Mentoring for Software Onboarding with Code Tours", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C07", "C:C09", "C:C10" ], "printed": true, "summary": "AI-assisted tours curated by experts outperform AI-generated-only code tours on a short comprehension test.", "limitation": "Five participants; no no-AI arm or long-run onboarding outcome.", "url": "https://arxiv.org/abs/2603.25391", "authors": "Kara", "year": "2026", "attributes": { "label": "LACY: Simulating Expert Mentoring for Software Onboarding with Code Tours", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Kara", "source": "https://arxiv.org/abs/2603.25391", "contribution": "AI-assisted tours curated by experts outperform AI-generated-only code tours on a short comprehension test.", "limitation": "Five participants; no no-AI arm or long-run onboarding outcome.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING; CH10:ARXIV_PDF_PAGES_VERIFIED_PUBLISHER_METADATA_CONFIRMED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Human cognitive load", "K:Skills formation and teaching", "K:Onboarding and developer fluency", "K:System understanding and rationale" ], "volumes": [ "V06" ] }, { "id": "W157", "label": "ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:What agents can do" ], "actual": [ "C:C09" ], "mapped": [ "C:C03", "C:C06", "C:C09", "C:C10" ], "printed": true, "summary": "Typed state pages and enforced write policy protect essential agent memory against compaction and reset failures.", "limitation": "Guarantees conditional on token-budget working set; limited trace and synthetic evaluation.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "authors": "Rafique", "year": "2026", "attributes": { "label": "ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Rafique", "source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "contribution": "Typed state pages and enforced write policy protect essential agent memory against compaction and reset failures.", "limitation": "Guarantees conditional on token-budget working set; limited trace and synthetic evaluation.", "manual_use": "Translate into a context-handoff pattern separating working context, durable facts and verified system knowledge.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:ORIGINAL_PDF_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Agent failure and escalation", "K:Dependencies and agent supply chain", "K:Specifications and governance", "K:Agent context and persistent memory", "K:Long-running agent execution", "K:Human-agent collaboration", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W158", "label": "Should I Give Up Now? Investigating LLM Pitfalls in Software Engineering", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:What agents can do" ], "actual": [ "C:C03", "C:C09" ], "mapped": [ "C:C03", "C:C09", "C:C10" ], "printed": true, "summary": "Wrong replies, overload and context loss can cause users to abandon AI assistance in a demanding web-development task.", "limitation": "Chat assistant rather than a modern autonomous tool-using agent.", "url": "https://arxiv.org/abs/2411.09916", "authors": "Tie", "year": "2026", "attributes": { "label": "Should I Give Up Now? Investigating LLM Pitfalls in Software Engineering", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Tie", "source": "https://arxiv.org/abs/2411.09916", "contribution": "Wrong replies, overload and context loss can cause users to abandon AI assistance in a demanding web-development task.", "limitation": "Chat assistant rather than a modern autonomous tool-using agent.", "manual_use": "Translate into a context-handoff pattern separating working context, durable facts and verified system knowledge.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Agent failure and escalation", "K:Agent context and persistent memory", "K:Long-running agent execution" ], "volumes": [ "V06" ] }, { "id": "W159", "label": "Memory Management and Contextual Consistency for Long-Running Low-Code Agents", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C09" ], "mapped": [ "C:C03", "C:C09", "C:C10", "C:C12" ], "printed": true, "summary": "Hybrid episodic and semantic storage with retention policies can improve long-horizon consistency and token efficiency.", "limitation": "Synthetic low-code trials; missing real SWE longitudinal validation.", "url": "https://arxiv.org/abs/2509.25250", "authors": "Xu", "year": "2026", "attributes": { "label": "Memory Management and Contextual Consistency for Long-Running Low-Code Agents", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Xu", "source": "https://arxiv.org/abs/2509.25250", "contribution": "Hybrid episodic and semantic storage with retention policies can improve long-horizon consistency and token efficiency.", "limitation": "Synthetic low-code trials; missing real SWE longitudinal validation.", "manual_use": "Translate into a context-handoff pattern separating working context, durable facts and verified system knowledge.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/abs/2509.25250", "publication_status_note": "Low-code agent-memory study; no software organization field results", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PREPRINT_PRIMARY_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Agent failure and escalation", "K:Agent context and persistent memory", "K:Economic costs and return", "K:Long-running agent execution", "K:Human-agent collaboration" ], "volumes": [ "V06" ] }, { "id": "W160", "label": "AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:What agents can do" ], "actual": [ "C:C09" ], "mapped": [ "C:C03", "C:C09", "C:C10" ], "printed": true, "summary": "Combining semantic facts with ordered episodes improves decisions over unstructured history in text environments.", "limitation": "Evaluated in games, not a production software repo.", "url": "https://arxiv.org/abs/2407.04363", "authors": "Anokhin", "year": "2025", "attributes": { "label": "AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents", "kind": "paper", "group": "System knowledge & memory", "year": "2025", "lead_author": "Anokhin", "source": "https://arxiv.org/abs/2407.04363", "contribution": "Combining semantic facts with ordered episodes improves decisions over unstructured history in text environments.", "limitation": "Evaluated in games, not a production software repo.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "General agent episodic knowledge graphs, not code-maintenance intervention", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PUBLISHED_PDF_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Benchmarks and construct validity", "K:Skills formation and teaching", "K:Agent context and persistent memory", "K:Long-running agent execution" ], "volumes": [ "V06" ] }, { "id": "W161", "label": "Examining ownership models in software teams: A systematic literature review and a replication study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Code quality & security" ], "actual": [], "mapped": [ "C:C05", "C:C09", "C:C10" ], "printed": true, "summary": "Ownership-defect correlations vary across datasets and cannot be used as immutable quality laws.", "limitation": "Nine-project replication changes sign relative to earlier Microsoft studies.", "url": "https://doi.org/10.1007/s10664-024-10538-5", "authors": "Koana", "year": "2024", "attributes": { "label": "Examining ownership models in software teams: A systematic literature review and a replication study", "kind": "paper", "group": "System knowledge & memory", "year": "2024", "lead_author": "Koana", "source": "https://doi.org/10.1007/s10664-024-10538-5", "contribution": "Ownership-defect correlations vary across datasets and cannot be used as immutable quality laws.", "limitation": "Nine-project replication changes sign relative to earlier Microsoft studies.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Literature synthesis", "editorial_priority": "B", "bibliography_year": "2024", "original_evidence_class": "Literature synthesis", "reviewed_evidence_class": "Literature synthesis", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1007/s10664-024-10538-5", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Ownership and knowledge transfer", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W162", "label": "40 Years of Designing Code Comprehension Experiments: A Systematic Mapping Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Verification & review" ], "actual": [ "C:C10" ], "mapped": [ "C:C07", "C:C08", "C:C09", "C:C10" ], "printed": true, "summary": "Program-comprehension experiments rarely test code personally authored by participants, leaving a major knowledge-transfer confound.", "limitation": "Maps pre-AI experiments; does not test agents directly.", "url": "https://doi.org/10.1145/3626522", "authors": "Wyrich", "year": "2024", "attributes": { "label": "40 Years of Designing Code Comprehension Experiments: A Systematic Mapping Study", "kind": "paper", "group": "System knowledge & memory", "year": "2024", "lead_author": "Wyrich", "source": "https://doi.org/10.1145/3626522", "contribution": "Program-comprehension experiments rarely test code personally authored by participants, leaving a major knowledge-transfer confound.", "limitation": "Maps pre-AI experiments; does not test agents directly.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "SYSTEMATIC_MAPPING_95_PRE_AI_EXPERIMENTS", "editorial_priority": "B", "bibliography_year": "2023", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "SYSTEMATIC_MAPPING_95_PRE_AI_EXPERIMENTS", "full_manuscript_audited": "yes_selected_methods", "cross_domain_boundary": "", "publication_year_from_independent_source": "2024", "publication_source_url": "https://doi.org/10.1145/3626522", "publication_status_note": "ACM Computing Surveys 56(4), 2024; 95 studies; 2026 corrigendum DOI 10.1145/3838282", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "FULLTEXT_PREPRINT_AND_PUBLISHED_CORRIGENDUM", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_MANUSCRIPT_SECTIONS", "audit_locator": "Original author preprint 2206.11102 Sections 2-5, PDF pp. 1-43; publication 2024; 2026 corrigendum 10.1145/3838282, section 1", "doi": "10.1145/3626522", "correction_warning": "2026 corrigendum DOI 10.1145/3838282: primary studies S1–S95 formerly mismatched; use corrected IDs only.", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Human cognitive load", "K:System understanding and rationale" ], "volumes": [ "V06" ] }, { "id": "W163", "label": "A Case Study of Onboarding in Software Teams: Tasks and Strategies", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C02", "C:C09", "C:C10" ], "printed": true, "summary": "Onboarding requires orchestrated starter tasks, mentoring and access to team knowledge rather than merely fast initial commits.", "limitation": "Mainly qualitative; duration not measured.", "url": "https://homepages.dcc.ufmg.br/~figueiredo/disciplinas/papers/icse2021ju.pdf", "authors": "Ju", "year": "2021", "attributes": { "label": "A Case Study of Onboarding in Software Teams: Tasks and Strategies", "kind": "paper", "group": "System knowledge & memory", "year": "2021", "lead_author": "Ju", "source": "https://homepages.dcc.ufmg.br/~figueiredo/disciplinas/papers/icse2021ju.pdf", "contribution": "Onboarding requires orchestrated starter tasks, mentoring and access to team knowledge rather than merely fast initial commits.", "limitation": "Mainly qualitative; duration not measured.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "MIXED_METHOD_SINGLE_COMPANY_CASE_STUDY", "editorial_priority": "C", "bibliography_year": "2021", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "MIXED_METHOD_SINGLE_COMPANY_CASE_STUDY", "full_manuscript_audited": "yes_selected_methods", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://homepages.dcc.ufmg.br/~figueiredo/disciplinas/papers/icse2021ju.pdf", "publication_status_note": "32 developer and 15 manager interviews; 189 developer/37 manager survey; Microsoft only; case study not random assignment", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "FULLTEXT_PRIMARY_METHODS_AND_RESULTS", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_MANUSCRIPT_SECTIONS", "audit_locator": "ICSE 2021 PDF pp. 1-3 (abstract, Methods, sample recruitment), Section VI threats", "doi": "10.1109/ICSE43902.2021.00063", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Skills formation and teaching", "K:Onboarding and developer fluency", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W164", "label": "Program Comprehension and Code Complexity Metrics: An fMRI Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Code quality & security" ], "actual": [], "mapped": [ "C:C05", "C:C09", "C:C10" ], "printed": true, "summary": "Common complexity metrics capture only part of human cognitive effort; text size and vocabulary also influence comprehension.", "limitation": "Nineteen participants, artificial snippets.", "url": "https://github.com/brains-on-code/fMRI-complexity-metrics-icse2021", "authors": "Peitek", "year": "2021", "attributes": { "label": "Program Comprehension and Code Complexity Metrics: An fMRI Study", "kind": "paper", "group": "System knowledge & memory", "year": "2021", "lead_author": "Peitek", "source": "https://github.com/brains-on-code/fMRI-complexity-metrics-icse2021", "contribution": "Common complexity metrics capture only part of human cognitive effort; text size and vocabulary also influence comprehension.", "limitation": "Nineteen participants, artificial snippets.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2021", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://github.com/brains-on-code/fMRI-complexity-metrics-icse2021", "pass7_identity_source_class": "author_software_repository", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Technical debt and complexity", "K:Human cognitive load", "K:System understanding and rationale" ], "volumes": [] }, { "id": "W165", "label": "Please Turn Your Cameras On: Remote Onboarding of Software Developers during a Pandemic", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Remote onboarding puts coordination and first-PR progress into focus; early contribution is not complete project fluency.", "limitation": "Survey report; does not measure months to mastery.", "url": "https://arxiv.org/abs/2011.08130", "authors": "Rodeghero", "year": "2021", "attributes": { "label": "Please Turn Your Cameras On: Remote Onboarding of Software Developers during a Pandemic", "kind": "paper", "group": "System knowledge & memory", "year": "2021", "lead_author": "Rodeghero", "source": "https://arxiv.org/abs/2011.08130", "contribution": "Remote onboarding puts coordination and first-PR progress into focus; early contribution is not complete project fluency.", "limitation": "Survey report; does not measure months to mastery.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2021", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Onboarding and developer fluency", "K:Remote work and apprenticeship", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W166", "label": "Comprehension of computer code relies primarily on domain-general executive brain regions", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Code comprehension draws heavily on general executive cognition, not ordinary natural-language comprehension alone.", "limitation": "Psychology of small programs rather than codebase ownership.", "url": "https://doi.org/10.7554/eLife.58906", "authors": "Ivanova", "year": "2020", "attributes": { "label": "Comprehension of computer code relies primarily on domain-general executive brain regions", "kind": "paper", "group": "System knowledge & memory", "year": "2020", "lead_author": "Ivanova", "source": "https://doi.org/10.7554/eLife.58906", "contribution": "Code comprehension draws heavily on general executive cognition, not ordinary natural-language comprehension alone.", "limitation": "Psychology of small programs rather than codebase ownership.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2020", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.7554/eLife.58906", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:System understanding and rationale", "K:Ownership and knowledge transfer" ], "volumes": [] }, { "id": "W167", "label": "A Look into Programmers' Heads", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Programming-language familiarity lowers cognitive effort during code reading.", "limitation": "Does not distinguish own code from unfamiliar team code.", "url": "https://doi.org/10.1109/TSE.2018.2863303", "authors": "Peitek", "year": "2020", "attributes": { "label": "A Look into Programmers' Heads", "kind": "paper", "group": "System knowledge & memory", "year": "2020", "lead_author": "Peitek", "source": "https://doi.org/10.1109/TSE.2018.2863303", "contribution": "Programming-language familiarity lowers cognitive effort during code reading.", "limitation": "Does not distinguish own code from unfamiliar team code.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2020", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1109/TSE.2018.2863303", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:System understanding and rationale" ], "volumes": [] }, { "id": "W168", "label": "Do you remember this source code?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C09" ], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "File-specific knowledge decays after contributions; own edits and share of code correlate with perceived familiarity.", "limitation": "Self-reported familiarity is not validated recall.", "url": "https://doi.org/10.1145/3180155.3180215", "authors": "Krüger", "year": "2018", "attributes": { "label": "Do you remember this source code?", "kind": "paper", "group": "System knowledge & memory", "year": "2018", "lead_author": "Krüger", "source": "https://doi.org/10.1145/3180155.3180215", "contribution": "File-specific knowledge decays after contributions; own edits and share of code correlate with perceived familiarity.", "limitation": "Self-reported familiarity is not validated recall.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Self-report / commercial evidence", "editorial_priority": "C", "bibliography_year": "2018", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "Self-report / commercial evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://doi.org/10.1145/3180155.3180215", "publication_status_note": "60 open-source developer survey, not an AI memory validation", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PUBLISHER_DOI_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1145/3180155.3180215", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust" ], "volumes": [ "V06" ] }, { "id": "W169", "label": "Simultaneous Measurement of Program Comprehension with fMRI and Eye Tracking: A Case Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Brain/gaze instrumentation for code understanding has important signal and measurement constraints.", "limitation": "More about measurement feasibility than AI intervention.", "url": "https://github.com/brains-on-code/simultaneous-fmri-and-eyetracking", "authors": "Peitek", "year": "2018", "attributes": { "label": "Simultaneous Measurement of Program Comprehension with fMRI and Eye Tracking: A Case Study", "kind": "paper", "group": "System knowledge & memory", "year": "2018", "lead_author": "Peitek", "source": "https://github.com/brains-on-code/simultaneous-fmri-and-eyetracking", "contribution": "Brain/gaze instrumentation for code understanding has important signal and measurement constraints.", "limitation": "More about measurement feasibility than AI intervention.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2018", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://github.com/brains-on-code/simultaneous-fmri-and-eyetracking", "pass7_identity_source_class": "author_software_repository", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W170", "label": "Measuring Program Comprehension: A Large-Scale Field Study with Professionals", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C01", "C:C09", "C:C10" ], "mapped": [ "C:C01", "C:C09", "C:C10" ], "printed": true, "summary": "Most development effort is spent understanding and navigating existing code, especially by newcomers.", "limitation": "Understanding inferred from telemetry, not observed; authorship unseparated.", "url": "https://xin-xia.github.io/publication/TSE17.pdf", "authors": "Xia", "year": "2018", "attributes": { "label": "Measuring Program Comprehension: A Large-Scale Field Study with Professionals", "kind": "paper", "group": "System knowledge & memory", "year": "2018", "lead_author": "Xia", "source": "https://xin-xia.github.io/publication/TSE17.pdf", "contribution": "Most development effort is spent understanding and navigating existing code, especially by newcomers.", "limitation": "Understanding inferred from telemetry, not observed; authorship unseparated.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2018", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PUBLISHER_ABSTRACT_VERIFIED; CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://baolingfeng.github.io/papers/tsecomprehension.pdf", "pass4_audit_version": "Author-hosted 23-page PDF versus TSE 44(10) 2018 publisher record", "pass4_audit_depth": "ORIGINAL_PDF_SELECTED_TABLES_JOURNAL_METADATA", "pass4_audit_methods_locators": "Author PDF p1, p7 Table3, p9 Table5, p22 threats; institutional published abstract", "pass4_audit_sample": "Author draft 79 developers/3244 hours; published journal abstract 78/3148, seven projects", "pass4_audit_observation": "Draft Table5 57.62% comprehension; journal abstract about 58%; draft Table3 2-developer validation", "pass4_audit_boundary": "Version sample-count conflict remains uncorrected without published full journal tables; not AI-specific", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "pass6_date": "2026-10-10", "pass6_locator": "https://baolingfeng.github.io/papers/tsecomprehension.pdf", "pass6_inspection_depth": "AUTHOR_23_PAGE_PDF_AND_PUBLISHED_ABSTRACT", "pass6_page_scope": "author p0; Table1 p3; Table5 p8; Monash journal metadata", "pass6_finding": "79 and 3244 author vs 78 and 3148 journal; author Table1 sums 79, exactly one developer and 96 hours difference", "pass6_limitation": "FINAL_JOURNAL_NUMERICAL_TABLES_UNAVAILABLE", "pass6_original_data_replicated": "NO", "pass8_primary_final_published_url": "https://xin-xia.github.io/publication/TSE17.pdf", "pass8_methods": "IEEE final p954 confirms explicit 96-hour excluded participant; journal Table1 p954 still sums 79; Table5 p959 same prior rates", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C09\", \"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:Onboarding and developer fluency", "K:System understanding and rationale", "K:Ownership and knowledge transfer", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W171", "label": "Revisiting Turnover-Induced Knowledge Loss in Software Projects", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C03", "C:C09", "C:C10" ], "printed": true, "summary": "Knowledge abandoned when contributors depart is concentrated in a tail of long-unowned files.", "limitation": "Code authorship serves as proxy for knowledge; agents threaten assumption.", "url": "https://doi.org/10.1109/ICSME.2017.64", "authors": "Nassif", "year": "2017", "attributes": { "label": "Revisiting Turnover-Induced Knowledge Loss in Software Projects", "kind": "paper", "group": "System knowledge & memory", "year": "2017", "lead_author": "Nassif", "source": "https://doi.org/10.1109/ICSME.2017.64", "contribution": "Knowledge abandoned when contributors depart is concentrated in a tail of long-unowned files.", "limitation": "Code authorship serves as proxy for knowledge; agents threaten assumption.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2017", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1109/ICSME.2017.64", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Agent failure and escalation", "K:Ownership and knowledge transfer", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W172", "label": "Measuring neural efficiency of program comprehension", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10", "C:C12" ], "printed": true, "summary": "Semantic cues like informative naming reduce cognitive effort during code comprehension.", "limitation": "Small trained sample; no AI and no realistic full projects.", "url": "https://doi.org/10.1145/3106237.3106268", "authors": "Siegmund", "year": "2017", "attributes": { "label": "Measuring neural efficiency of program comprehension", "kind": "paper", "group": "System knowledge & memory", "year": "2017", "lead_author": "Siegmund", "source": "https://doi.org/10.1145/3106237.3106268", "contribution": "Semantic cues like informative naming reduce cognitive effort during code comprehension.", "limitation": "Small trained sample; no AI and no realistic full projects.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2017", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1145/3106237.3106268", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:System understanding and rationale", "K:Agent context and persistent memory", "K:Economic costs and return", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W173", "label": "Quantifying and Mitigating Turnover-Induced Knowledge Loss: Case Studies of Chrome and a Project at Avaya", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C09", "C:C11" ], "mapped": [ "C:C06", "C:C09", "C:C10", "C:C11" ], "printed": true, "summary": "Developer departure leaves knowledge coverage gaps; successor assignment can partially reduce them.", "limitation": "Code-blame ownership proxy may fail when agents commit code.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "authors": "Rigby", "year": "2016", "attributes": { "label": "Quantifying and Mitigating Turnover-Induced Knowledge Loss: Case Studies of Chrome and a Project at Avaya", "kind": "paper", "group": "System knowledge & memory", "year": "2016", "lead_author": "Rigby", "source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "contribution": "Developer departure leaves knowledge coverage gaps; successor assignment can partially reduce them.", "limitation": "Code-blame ownership proxy may fail when agents commit code.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2016", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:ORIGINAL_PDF_VERIFIED; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Vulnerability and secure code", "K:Ownership and knowledge transfer" ], "volumes": [ "V06" ] }, { "id": "W174", "label": "Impact of Developer Turnover on Quality in Open-Source Software", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Code quality & security" ], "actual": [], "mapped": [ "C:C05", "C:C09", "C:C10" ], "printed": true, "summary": "External contributor churn can affect downstream quality and code stewardship.", "limitation": "Effect sizes not retrieved in annotated bibliography.", "url": "https://doi.org/10.1145/2786805.2786870", "authors": "Foucault", "year": "2015", "attributes": { "label": "Impact of Developer Turnover on Quality in Open-Source Software", "kind": "paper", "group": "System knowledge & memory", "year": "2015", "lead_author": "Foucault", "source": "https://doi.org/10.1145/2786805.2786870", "contribution": "External contributor churn can affect downstream quality and code stewardship.", "limitation": "Effect sizes not retrieved in annotated bibliography.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2015", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1145/2786805.2786870", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Ownership and knowledge transfer" ], "volumes": [] }, { "id": "W175", "label": "Code Ownership and Software Quality: A Replication Study", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Code quality & security" ], "actual": [ "C:C01", "C:C05" ], "mapped": [ "C:C01", "C:C04", "C:C05", "C:C09", "C:C10" ], "printed": true, "summary": "Weak code ownership predicts defects in some settings while intentional shared ownership can be healthy.", "limitation": "Regression only, ownership meaning depends on organizational context.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "authors": "Greiler", "year": "2015", "attributes": { "label": "Code Ownership and Software Quality: A Replication Study", "kind": "paper", "group": "System knowledge & memory", "year": "2015", "lead_author": "Greiler", "source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "contribution": "Weak code ownership predicts defects in some settings while intentional shared ownership can be healthy.", "limitation": "Regression only, ownership meaning depends on organizational context.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2015", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:AUTHOR_CAMERA_READY_PDF_LOCATED; CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C05\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Specifications and governance", "K:Ownership and knowledge transfer", "K:Agent context and persistent memory", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W176", "label": "I Know What You Did Last Summer — An Investigation of How Developers Spend Their Time", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C01" ], "mapped": [ "C:C01", "C:C09", "C:C10" ], "printed": true, "summary": "Understanding consumes a larger share of developer time than typing in an observed Smalltalk setting.", "limitation": "One IDE ecosystem and mixed student/professional cohort.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "authors": "Minelli", "year": "2015", "attributes": { "label": "I Know What You Did Last Summer — An Investigation of How Developers Spend Their Time", "kind": "paper", "group": "System knowledge & memory", "year": "2015", "lead_author": "Minelli", "source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "contribution": "Understanding consumes a larger share of developer time than typing in an observed Smalltalk setting.", "limitation": "One IDE ecosystem and mixed student/professional cohort.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2015", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C01\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Skills formation and teaching", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W177", "label": "Stuck and Frustrated or in Flow and Happy: Sensing Developers' Emotions and Progress", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C02", "C:C09", "C:C10", "C:C12" ], "printed": true, "summary": "Sensing subjective strain and flow might complement throughput metrics when evaluating human-agent collaboration.", "limitation": "Tiny sample and predictor errors; monitoring raises privacy concerns.", "url": "https://doi.org/10.1109/ICSE.2015.334", "authors": "Müller", "year": "2015", "attributes": { "label": "Stuck and Frustrated or in Flow and Happy: Sensing Developers' Emotions and Progress", "kind": "paper", "group": "System knowledge & memory", "year": "2015", "lead_author": "Müller", "source": "https://doi.org/10.1109/ICSE.2015.334", "contribution": "Sensing subjective strain and flow might complement throughput metrics when evaluating human-agent collaboration.", "limitation": "Tiny sample and predictor errors; monitoring raises privacy concerns.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2015", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "pass7_verified_primary_locator": "https://doi.org/10.1109/ICSE.2015.334", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Developer workflow and adoption", "K:Employment and early-career roles", "K:Human-agent collaboration", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W178", "label": "Ramp-Up Journey of New Hires: Tug of War of Aids and Impediments", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "First commit arrives well before full file-level breadth and ramp-up; different activity measures plateau at different times.", "limitation": "Absolute durations withheld; first PR is invalid proxy for competency.", "url": "https://doi.org/10.1109/ESEM.2015.7321212", "authors": "Rastogi", "year": "2015", "attributes": { "label": "Ramp-Up Journey of New Hires: Tug of War of Aids and Impediments", "kind": "paper", "group": "System knowledge & memory", "year": "2015", "lead_author": "Rastogi", "source": "https://doi.org/10.1109/ESEM.2015.7321212", "contribution": "First commit arrives well before full file-level breadth and ramp-up; different activity measures plateau at different times.", "limitation": "Absolute durations withheld; first PR is invalid proxy for competency.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2015", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://doi.org/10.1109/ESEM.2015.7321212", "publication_status_note": "2015 ESEM ramp-up paper; distinct from later similarly named paper", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PUBLISHER_DOI_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1109/ESEM.2015.7321212", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Onboarding and developer fluency", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W179", "label": "A systematic literature review on the usage of eye-tracking in software engineering", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Existing gaze-based studies seldom isolate effects of own-code versus other-code understanding.", "limitation": "Predates LLM tooling; study design gaps not outcome evidence.", "url": "https://doi.org/10.1016/j.infsof.2015.06.008", "authors": "Sharafi", "year": "2015", "attributes": { "label": "A systematic literature review on the usage of eye-tracking in software engineering", "kind": "paper", "group": "System knowledge & memory", "year": "2015", "lead_author": "Sharafi", "source": "https://doi.org/10.1016/j.infsof.2015.06.008", "contribution": "Existing gaze-based studies seldom isolate effects of own-code versus other-code understanding.", "limitation": "Predates LLM tooling; study design gaps not outcome evidence.", "manual_use": "Compare human-on-human, human-on-agent and AI-on-human review and record review effort, precision and real defects.", "evidence_class": "Literature synthesis", "editorial_priority": "B", "bibliography_year": "2015", "original_evidence_class": "Literature synthesis", "reviewed_evidence_class": "Literature synthesis", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1016/j.infsof.2015.06.008", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Developer workflow and adoption", "K:Human cognitive load", "K:System understanding and rationale" ], "volumes": [] }, { "id": "W180", "label": "Using psycho-physiological measures to assess task difficulty in software development", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10", "C:C12" ], "printed": true, "summary": "Multi-sensor measurements may detect task difficulty and cognitive burden more directly than edit counts.", "limitation": "Performance on new programmers weaker; implementation costs and privacy limits.", "url": "https://www.microsoft.com/en-us/research/publication/using-psycho-physiological-measures-to-assess-task-difficulty-in-software-development/", "authors": "Fritz", "year": "2014", "attributes": { "label": "Using psycho-physiological measures to assess task difficulty in software development", "kind": "paper", "group": "System knowledge & memory", "year": "2014", "lead_author": "Fritz", "source": "https://www.microsoft.com/en-us/research/publication/using-psycho-physiological-measures-to-assess-task-difficulty-in-software-development/", "contribution": "Multi-sensor measurements may detect task difficulty and cognitive burden more directly than edit counts.", "limitation": "Performance on new programmers weaker; implementation costs and privacy limits.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2014", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://www.microsoft.com/en-us/research/publication/using-psycho-physiological-measures-to-assess-task-difficulty-in-software-development/", "pass7_identity_source_class": "institutional_publication_record", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:Economic costs and return", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W181", "label": "Understanding understanding source code with functional magnetic resonance imaging", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Brain activation differs between true program comprehension and superficial syntax spotting.", "limitation": "Contrived snippets with obscured identifiers.", "url": "https://doi.org/10.1145/2568225.2568252", "authors": "Siegmund", "year": "2014", "attributes": { "label": "Understanding understanding source code with functional magnetic resonance imaging", "kind": "paper", "group": "System knowledge & memory", "year": "2014", "lead_author": "Siegmund", "source": "https://doi.org/10.1145/2568225.2568252", "contribution": "Brain activation differs between true program comprehension and superficial syntax spotting.", "limitation": "Contrived snippets with obscured identifiers.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Benchmark / controlled laboratory", "editorial_priority": "B", "bibliography_year": "2014", "original_evidence_class": "Benchmark / controlled laboratory", "reviewed_evidence_class": "Benchmark / controlled laboratory", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://doi.org/10.1145/2568225.2568252", "pass7_identity_source_class": "publisher_doi", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Human cognitive load", "K:System understanding and rationale" ], "volumes": [] }, { "id": "W182", "label": "Don't Touch My Code! Examining the Effects of Ownership on Software Quality", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Code quality & security" ], "actual": [ "C:C05", "C:C09" ], "mapped": [ "C:C02", "C:C05", "C:C09", "C:C10" ], "printed": true, "summary": "Low-concentration human code ownership correlates with defects; suggests stewardship matters.", "limitation": "Product-level correlation and human-authorship assumption not portable unchanged to agent output.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "authors": "Bird", "year": "2011", "attributes": { "label": "Don't Touch My Code! Examining the Effects of Ownership on Software Quality", "kind": "paper", "group": "System knowledge & memory", "year": "2011", "lead_author": "Bird", "source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "contribution": "Low-concentration human code ownership correlates with defects; suggests stewardship matters.", "limitation": "Product-level correlation and human-authorship assumption not portable unchanged to agent output.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2011", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:PUBLISHER_RECORD_AND_AUTHOR_SOURCE_LOCATED; CH09:ORIGINAL_PDF_VERIFIED", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C05\", \"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Ownership and knowledge transfer" ], "volumes": [ "V06" ] }, { "id": "W183", "label": "Moving into a New Software Project Landscape", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "New developers need exploration and environment setup before completing useful changes, regardless of code generation rate.", "limitation": "Small heterogeneous IBM samples, legacy context.", "url": "https://research.ibm.com/publications/moving-into-a-new-software-project-landscape", "authors": "Dagenais", "year": "2010", "attributes": { "label": "Moving into a New Software Project Landscape", "kind": "paper", "group": "System knowledge & memory", "year": "2010", "lead_author": "Dagenais", "source": "https://research.ibm.com/publications/moving-into-a-new-software-project-landscape", "contribution": "New developers need exploration and environment setup before completing useful changes, regardless of code generation rate.", "limitation": "Small heterogeneous IBM samples, legacy context.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2010", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://research.ibm.com/publications/moving-into-a-new-software-project-landscape", "pass7_identity_source_class": "institutional_publication_record", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Onboarding and developer fluency", "K:System understanding and rationale", "K:Agent context and persistent memory", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W184", "label": "Developer Fluency: Achieving True Mastery in Software Projects", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Newcomers can match task counts long before developing fluency for difficult central components.", "limitation": "Three-plus-year mastery is a hypothesis, not directly measured universal threshold.", "url": "https://doi.org/10.1145/1882291.1882313", "authors": "Zhou", "year": "2010", "attributes": { "label": "Developer Fluency: Achieving True Mastery in Software Projects", "kind": "paper", "group": "System knowledge & memory", "year": "2010", "lead_author": "Zhou", "source": "https://doi.org/10.1145/1882291.1882313", "contribution": "Newcomers can match task counts long before developing fluency for difficult central components.", "limitation": "Three-plus-year mastery is a hypothesis, not directly measured universal threshold.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2010", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://doi.org/10.1145/1882291.1882313", "publication_status_note": "2010 conference; full method tables pending", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "PUBLISHER_DOI_RECORD", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1145/1882291.1882313", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Onboarding and developer fluency", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W185", "label": "Succession: Measuring Transfer of Code and Developer Productivity", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C09", "C:C11" ], "mapped": [ "C:C02", "C:C09", "C:C10", "C:C11" ], "printed": true, "summary": "Ownership transfer across teams or geography may lower successor effectiveness without deliberate knowledge handoff.", "limitation": "Past corporate development model; not agent-mediated work.", "url": "https://mockus.org/papers/succession.pdf", "authors": "Mockus", "year": "2009", "attributes": { "label": "Succession: Measuring Transfer of Code and Developer Productivity", "kind": "paper", "group": "System knowledge & memory", "year": "2009", "lead_author": "Mockus", "source": "https://mockus.org/papers/succession.pdf", "contribution": "Ownership transfer across teams or geography may lower successor effectiveness without deliberate knowledge handoff.", "limitation": "Past corporate development model; not agent-mediated work.", "manual_use": "Use to teach a metrics hierarchy: generated code → integrated change → deployed outcome → customer value.", "evidence_class": "INDUSTRIAL_OBSERVATIONAL_SUCCESSION_REGRESSION", "editorial_priority": "A", "bibliography_year": "2009", "original_evidence_class": "Quasi-experimental / matched observation", "reviewed_evidence_class": "INDUSTRIAL_OBSERVATIONAL_SUCCESSION_REGRESSION", "full_manuscript_audited": "yes_selected_methods", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://mockus.org/papers/succession.pdf", "publication_status_note": "ICSE 2009 Sections 5 and 6, Tables 1-2; 10 identified succession cases and 1,012 mentor-follower pairs", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "FULLTEXT_PRIMARY_METHODS_TABLES", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_MANUSCRIPT_SECTIONS", "audit_locator": "ICSE 2009 PDF p. 6 Table 1; p. 9 Table 2 (zero-based PDF page indices 5 and 8), Section 6.3-6.4", "doi": "10.1109/ICSE.2009.5070509", "previous_chapter_audit_registers": "CH09:ORIGINAL_ABSTRACT_AND_METADATA_VERIFIED; CH10:FULL_TEXT_REVIEW_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C09\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Ownership and knowledge transfer", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W186", "label": "Maintaining Mental Models: A Study of Developer Work Habits", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C01", "C:C09" ], "mapped": [ "C:C01", "C:C09", "C:C10" ], "printed": true, "summary": "Developers struggle particularly with others' code and hidden design rationale, making explanation provenance an asset.", "limitation": "Perceived problem ratings, not timed comprehension measures.", "url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/p492-latoza.pdf", "authors": "LaToza", "year": "2006", "attributes": { "label": "Maintaining Mental Models: A Study of Developer Work Habits", "kind": "paper", "group": "System knowledge & memory", "year": "2006", "lead_author": "LaToza", "source": "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/p492-latoza.pdf", "contribution": "Developers struggle particularly with others' code and hidden design rationale, making explanation provenance an asset.", "limitation": "Perceived problem ratings, not timed comprehension measures.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "EXPLORATORY_SINGLE_COMPANY_SURVEY_AND_INTERVIEWS", "editorial_priority": "C", "bibliography_year": "2006", "original_evidence_class": "Self-report / commercial evidence", "reviewed_evidence_class": "EXPLORATORY_SINGLE_COMPANY_SURVEY_AND_INTERVIEWS", "full_manuscript_audited": "yes_selected_methods", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/p492-latoza.pdf", "publication_status_note": "ICSE 2006 Section 3.3, 157 and 187 responses from separate invitations of 1000 each; 11 interviews; selection bias not measured", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "FULLTEXT_PRIMARY_METHODS_TABLES", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_MANUSCRIPT_SECTIONS", "audit_locator": "ICSE 2006 PDF pp. 2-4, Section 3 method, 3.3 sampling and Table 1", "doi": "10.1145/1134285.1134355", "previous_chapter_audit_registers": "CH09:AUTHOR_INSTITUTIONAL_ABSTRACT_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C01\", \"C:C09\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Automation bias and trust", "K:Human cognitive load", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W187", "label": "Globalization by Chunking: A Quantitative Approach", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [ "C:C10" ], "mapped": [ "C:C02", "C:C09", "C:C10" ], "printed": true, "summary": "New engineers took more than a year on average to reach a change-count plateau in one telecommunications system.", "limitation": "One team and counting commits; does not measure full mastery or AI effects.", "url": "https://mockus.org/papers/chunking.pdf", "authors": "Mockus", "year": "2001", "attributes": { "label": "Globalization by Chunking: A Quantitative Approach", "kind": "paper", "group": "System knowledge & memory", "year": "2001", "lead_author": "Mockus", "source": "https://mockus.org/papers/chunking.pdf", "contribution": "New engineers took more than a year on average to reach a change-count plateau in one telecommunications system.", "limitation": "One team and counting commits; does not measure full mastery or AI effects.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2001", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no_primary_locator_only", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://mockus.org/papers/chunking.pdf", "publication_status_note": "Original author-hosted journal paper; full-text inspection not completed", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "source_verification_method": "AUTHOR_FULL_TEXT_LOCATOR_ONLY", "audit_date": "2026-10-10", "audit_depth": "PRIMARY_METADATA_LOCATOR", "audit_locator": "Primary publication record; page-level study audit pending", "doi": "10.1109/52.914737", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C10\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Evaluation methodology and baselines" ], "volumes": [ "V06" ] }, { "id": "W188", "label": "The Ramp-Up Problem in Software Projects: A Case Study of How Software Immigrants Naturalize", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory", "T:Skills & learning" ], "actual": [], "mapped": [ "C:C02", "C:C09", "C:C10" ], "printed": true, "summary": "Environmental access and mentoring dominate early onboarding, with independence possible before comprehensive system understanding.", "limitation": "N=4; expert estimate for six-to-twelve-month productivity not measured.", "url": "https://dl.acm.org/doi/10.5555/302163.302199", "authors": "Sim", "year": "1998", "attributes": { "label": "The Ramp-Up Problem in Software Projects: A Case Study of How Software Immigrants Naturalize", "kind": "paper", "group": "System knowledge & memory", "year": "1998", "lead_author": "Sim", "source": "https://dl.acm.org/doi/10.5555/302163.302199", "contribution": "Environmental access and mentoring dominate early onboarding, with independence possible before comprehensive system understanding.", "limitation": "N=4; expert estimate for six-to-twelve-month productivity not measured.", "manual_use": "Use as a baseline when designing AI-supported onboarding with independent comprehension and retention tests.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "1998", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH10:FULL_TEXT_REVIEW_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass7_verified_primary_locator": "https://dl.acm.org/doi/10.5555/302163.302199", "pass7_identity_source_class": "publisher_record", "pass7_methods_replicated": "NO", "legacy_editorial_source": "https://www.sepolimi.com/p/se-ai-bibliography-system-knowledge-memory", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Output versus shipped value", "K:Human cognitive load", "K:Skills formation and teaching", "K:Onboarding and developer fluency", "K:System understanding and rationale", "K:Evaluation methodology and baselines" ], "volumes": [] }, { "id": "W189", "label": "The Substrate Collapse: AI Code Generation Invalidates Authorship-Based Knowledge Metrics", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [ "C:C05", "C:C09", "C:C11" ], "mapped": [ "C:C05", "C:C09", "C:C10", "C:C11" ], "printed": true, "summary": "Authorship-based truck-factor and ownership metrics may become misleading once agents author code without human understanding.", "limitation": "Central insight is conceptual; no empirical recalibration proposed.", "url": "https://arxiv.org/abs/2606.20882", "authors": "Wheeler", "year": "2026", "attributes": { "label": "The Substrate Collapse: AI Code Generation Invalidates Authorship-Based Knowledge Metrics", "kind": "paper", "group": "System knowledge & memory", "year": "2026", "lead_author": "Wheeler", "source": "https://arxiv.org/abs/2606.20882", "contribution": "Authorship-based truck-factor and ownership metrics may become misleading once agents author code without human understanding.", "limitation": "Central insight is conceptual; no empirical recalibration proposed.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Theory / argument (not a new result)", "editorial_priority": "C", "bibliography_year": "2026", "original_evidence_class": "Theory / argument (not a new result)", "reviewed_evidence_class": "Theory / argument (not a new result)", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH05:FULL_TEXT_OPENED_METHODS_PENDING; CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING; CH11:FULL_TEXT_PENDING", "previous_chapter_audit_count": "3", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "pass4_audit_primary_url": "https://arxiv.org/html/2606.20882", "pass4_audit_version": "arXiv:2606.20882v1 (2026-06-18)", "pass4_audit_depth": "ORIGINAL_HTML_CONCEPTUAL_METHOD", "pass4_audit_methods_locators": "Premise, measurement critique and explicit scope sections", "pass4_audit_sample": "No new developer sample or fresh authorship-truck-factor validation", "pass4_audit_observation": "Argues commits and authorship are no longer reliable proxies for comprehension under generation", "pass4_audit_boundary": "Argument is plausible but does not statistically prove invalidity for every repository", "pass4_audit_original_data_replication": "NO", "pass4_audit_provenance": "PASS4_SELECTED_PRIMARY_2026-10-10", "pass4_audit_date": "2026-10-10", "ndse2_actual_chapters_json": "[\"C:C05\", \"C:C09\", \"C:C11\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Skills formation and teaching", "K:System understanding and rationale", "K:Ownership and knowledge transfer" ], "volumes": [ "V06" ] }, { "id": "W190", "label": "How do Humans and LLMs Process Confusing Code?", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:System knowledge & memory" ], "actual": [], "mapped": [ "C:C09", "C:C10" ], "printed": true, "summary": "Model perplexity and human confusion can correlate on difficult source lines, suggesting possible code-comprehension diagnostics.", "limitation": "Reused small EEG dataset and one model; correlation not general ability.", "url": "https://arxiv.org/abs/2508.18547", "authors": "Abdelsalam", "year": "2025", "attributes": { "label": "How do Humans and LLMs Process Confusing Code?", "kind": "paper", "group": "System knowledge & memory", "year": "2025", "lead_author": "Abdelsalam", "source": "https://arxiv.org/abs/2508.18547", "contribution": "Model perplexity and human confusion can correlate on difficult source lines, suggesting possible code-comprehension diagnostics.", "limitation": "Reused small EEG dataset and one model; correlation not general ability.", "manual_use": "Preserve human system comprehension, provenance and durable agent context.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2025", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH09:PRIMARY_FULL_TEXT_AUDIT_PENDING", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Code reuse and duplication", "K:Human cognitive load", "K:System understanding and rationale", "K:Dataset provenance and dependency" ], "volumes": [] }, { "id": "W191", "label": "Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:What agents can do", "T:Verification & review" ], "actual": [ "C:C03", "C:C04" ], "mapped": [ "C:C01", "C:C03", "C:C04", "C:C07", "C:C08" ], "printed": true, "summary": "Rejected agent PRs reveal recurring limits in requirement understanding, repository fit and coordination with maintainers.", "limitation": "Failure coding depends on visible GitHub information; shared AIDev sample.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-what-agents-can-do", "authors": "Ehsani", "year": "2026", "attributes": { "label": "Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub", "kind": "paper", "group": "What agents can do", "year": "2026", "lead_author": "Ehsani", "source": "https://www.sepolimi.com/p/se-ai-bibliography-what-agents-can-do", "contribution": "Rejected agent PRs reveal recurring limits in requirement understanding, repository fit and coordination with maintainers.", "limitation": "Failure coding depends on visible GitHub information; shared AIDev sample.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:ARXIV_ABSTRACT_VERIFIED", "previous_chapter_audit_count": "1", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C04\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Review capacity and maintainers", "K:Agent failure and escalation", "K:System understanding and rationale", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W192", "label": "AIDev: Studying AI Coding Agents on GitHub", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:What agents can do", "T:Verification & review" ], "actual": [ "C:C07" ], "mapped": [ "C:C03", "C:C07", "C:C08" ], "printed": true, "summary": "Supplies a reusable 932791-PR universe and a curated 33596-PR subset that underpins many agent outcome studies.", "limitation": "Shared data are not independent replications; five agents and snapshot through mid-2025.", "url": "https://arxiv.org/html/2602.09185", "authors": "Li", "year": "2026", "attributes": { "label": "AIDev: Studying AI Coding Agents on GitHub", "kind": "paper", "group": "What agents can do", "year": "2026", "lead_author": "Li", "source": "https://www.sepolimi.com/p/se-ai-bibliography-what-agents-can-do", "contribution": "Supplies a reusable 932791-PR universe and a curated 33596-PR subset that underpins many agent outcome studies.", "limitation": "Shared data are not independent replications; five agents and snapshot through mid-2025.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "https://arxiv.org/html/2602.09185", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "audit_locator": "arXiv 2602.09185 html Introduction and dataset description; chapter 7 earlier audit primary-source register", "data_snapshot_warning": "Dataset observational and shared by W068/W071; overlapping observations are not independent replication.", "previous_chapter_audit_registers": "CH03:ARXIV_ABSTRACT_VERIFIED; CH07:FULLTEXT_HTML_DATASET", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Independent verification and oracles", "K:Evaluation methodology and baselines", "K:Dataset provenance and dependency" ], "volumes": [ "V06" ] }, { "id": "W193", "label": "MirrorCode: Evidence that AI can already do some weeks-long coding tasks", "kind": "paper", "collection": "W", "category": null, "streams": [ "T:What agents can do" ], "actual": [ "C:C03", "C:C07" ], "mapped": [ "C:C03", "C:C07" ], "printed": true, "summary": "Agents can replicate substantial multi-file implementation work in a constrained exercise, challenging simplistic duration ceilings.", "limitation": "Human-hours counterfactual inferred; not general work-hour substitution or deployment readiness.", "url": "https://www.sepolimi.com/p/se-ai-bibliography-what-agents-can-do", "authors": "METR / Epoch AI", "year": "2026", "attributes": { "label": "MirrorCode: Evidence that AI can already do some weeks-long coding tasks", "kind": "paper", "group": "What agents can do", "year": "2026", "lead_author": "METR / Epoch AI", "source": "https://www.sepolimi.com/p/se-ai-bibliography-what-agents-can-do", "contribution": "Agents can replicate substantial multi-file implementation work in a constrained exercise, challenging simplistic duration ceilings.", "limitation": "Human-hours counterfactual inferred; not general work-hour substitution or deployment readiness.", "manual_use": "Make the engineering response an explicit scoped permission, testable gate or human escalation criterion.", "evidence_class": "Observational / qualitative evidence", "editorial_priority": "B", "bibliography_year": "2026", "original_evidence_class": "Observational / qualitative evidence", "reviewed_evidence_class": "Observational / qualitative evidence", "full_manuscript_audited": "no", "cross_domain_boundary": "", "publication_year_from_independent_source": "", "publication_source_url": "", "publication_status_note": "", "section_id": "", "summary": "", "method_status": "", "provenance": "", "node_class": "LEGACY_EDITORIAL_GRAPH", "baseline_provenance": "2026-10-09 corrected editorial crosswalk", "previous_chapter_audit_registers": "CH03:NOT_INDEPENDENTLY_INSPECTED; CH07:FULLTEXT_INSTITUTIONAL", "previous_chapter_audit_count": "2", "previous_audit_warning": "Archived self-reported inspection depth; no independent reinspection from these archive records in 2026-10-10 pass.", "ndse2_actual_chapters_json": "[\"C:C03\", \"C:C07\"]", "ndse2_in_bibliography": true, "ndse2_citation_basis": "Final 13.7.1 active EN/ITA source tree; index links and nocite are not chapter citations" }, "topics": [ "K:Controlled productivity evidence", "K:Evaluation methodology and baselines", "K:Long-running agent execution" ], "volumes": [ "V06" ] } ] }