{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FJMALU2FFM5H3PLFL3EEU3WHFK","short_pith_number":"pith:FJMALU2F","schema_version":"1.0","canonical_sha256":"2a5805d3452b3a7dbd655ec84a6ec72a80057f0305b517dcfac4cc1e63691376","source":{"kind":"arxiv","id":"2603.27130","version":3},"attestation_state":"computed","paper":{"title":"A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dongfang Zhao, Haixu Tang, Hang Zhang, Tianhao Mao, Xiaofeng Wang","submitted_at":"2026-03-28T04:40:44Z","abstract_excerpt":"Large language models (LLMs) are rapidly transforming software engineering by enabling developers to generate code ranging from small snippets to entire projects. As AI-assisted code becomes increasingly integrated into real-world systems, understanding its characteristics and impact is critical. Existing study on AI-generated code is usually limited in the lab setting with synthetic benchmarks and small-scale coding tasks and covers limited metrics. AI-assisted code's manifestation in real-world codebases and its differences between human-written one remain unclear. To close this gap, we perf"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2603.27130","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T04:40:44Z","cross_cats_sorted":[],"title_canon_sha256":"0d52eefd37182bd8a6f845fa5627cee2925f7780a002b86b42264fa8a5b8ea4d","abstract_canon_sha256":"e25d66c41cab76f4ecd1f14ed7eb1e322c6beab6199416e3bfa3acd7882e3f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:53.361396Z","signature_b64":"ZnHtcOBDHSsTpZVBE8HiVqfuuePgknq7eUEvTiB6+xsmf5EoGHIHQ+ZQudGZLFUncE3Vy677HGATMbD017LpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a5805d3452b3a7dbd655ec84a6ec72a80057f0305b517dcfac4cc1e63691376","last_reissued_at":"2026-07-03T00:16:53.361014Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:53.361014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dongfang Zhao, Haixu Tang, Hang Zhang, Tianhao Mao, Xiaofeng Wang","submitted_at":"2026-03-28T04:40:44Z","abstract_excerpt":"Large language models (LLMs) are rapidly transforming software engineering by enabling developers to generate code ranging from small snippets to entire projects. As AI-assisted code becomes increasingly integrated into real-world systems, understanding its characteristics and impact is critical. Existing study on AI-generated code is usually limited in the lab setting with synthetic benchmarks and small-scale coding tasks and covers limited metrics. AI-assisted code's manifestation in real-world codebases and its differences between human-written one remain unclear. To close this gap, we perf"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our study provides a comprehensive view of the characteristics of AI-generated code in practice and highlights how AI-assisted development differs from conventional human-driven development.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The detection pipeline that combines heuristic filtering with LLM-based classification accurately identifies AI-generated code at scale with acceptable error rates.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A large-scale study of real-world repositories finds that AI-generated code differs from human-written code in complexity, structural traits, defect indicators, and commit-level activity patterns.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e8e798e5acf199e2fd998a8ce479e8a2d3b88adc11e56494aac0254ba15336d3"},"source":{"id":"2603.27130","kind":"arxiv","version":3},"verdict":{"id":"1c88ab24-b03a-4899-b48e-b5588ee8a383","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T22:45:00.905965Z","strongest_claim":"Our study provides a comprehensive view of the characteristics of AI-generated code in practice and highlights how AI-assisted development differs from conventional human-driven development.","one_line_summary":"A large-scale study of real-world repositories finds that AI-generated code differs from human-written code in complexity, structural traits, defect indicators, and commit-level activity patterns.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The detection pipeline that combines heuristic filtering with LLM-based classification accurately identifies AI-generated code at scale with acceptable error rates.","pith_extraction_headline":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.27130/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b93c9a9d9d948bce1d12f32a5f27b53876e0f42cb4f567b8b3f471caabbde59b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.27130","created_at":"2026-07-03T00:16:53.361071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27130v3","created_at":"2026-07-03T00:16:53.361071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27130","created_at":"2026-07-03T00:16:53.361071+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJMALU2FFM5H","created_at":"2026-07-03T00:16:53.361071+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJMALU2FFM5H3PLF","created_at":"2026-07-03T00:16:53.361071+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJMALU2F","created_at":"2026-07-03T00:16:53.361071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07980","citing_title":"3100 Opinions on Code Review in an AI World: Building Causal Theory from Practitioner Discourse","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK","json":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK.json","graph_json":"https://pith.science/api/pith-number/FJMALU2FFM5H3PLFL3EEU3WHFK/graph.json","events_json":"https://pith.science/api/pith-number/FJMALU2FFM5H3PLFL3EEU3WHFK/events.json","paper":"https://pith.science/paper/FJMALU2F"},"agent_actions":{"view_html":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK","download_json":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK.json","view_paper":"https://pith.science/paper/FJMALU2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27130&json=true","fetch_graph":"https://pith.science/api/pith-number/FJMALU2FFM5H3PLFL3EEU3WHFK/graph.json","fetch_events":"https://pith.science/api/pith-number/FJMALU2FFM5H3PLFL3EEU3WHFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK/action/storage_attestation","attest_author":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK/action/author_attestation","sign_citation":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK/action/citation_signature","submit_replication":"https://pith.science/pith/FJMALU2FFM5H3PLFL3EEU3WHFK/action/replication_record"}},"created_at":"2026-07-03T00:16:53.361071+00:00","updated_at":"2026-07-03T00:16:53.361071+00:00"}