{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FJMALU2FFM5H3PLFL3EEU3WHFK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e25d66c41cab76f4ecd1f14ed7eb1e322c6beab6199416e3bfa3acd7882e3f50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T04:40:44Z","title_canon_sha256":"0d52eefd37182bd8a6f845fa5627cee2925f7780a002b86b42264fa8a5b8ea4d"},"schema_version":"1.0","source":{"id":"2603.27130","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.27130","created_at":"2026-07-03T00:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2603.27130v3","created_at":"2026-07-03T00:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27130","created_at":"2026-07-03T00:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"FJMALU2FFM5H","created_at":"2026-07-03T00:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"FJMALU2FFM5H3PLF","created_at":"2026-07-03T00:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"FJMALU2F","created_at":"2026-07-03T00:16:53Z"}],"graph_snapshots":[{"event_id":"sha256:01f87cf318279441df1dd089fae123818f4ce35a3d8edbbfbba770afa3963b94","target":"graph","created_at":"2026-07-03T00:16:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The detection pipeline that combines heuristic filtering with LLM-based classification accurately identifies AI-generated code at scale with acceptable error rates."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution."}],"snapshot_sha256":"e8e798e5acf199e2fd998a8ce479e8a2d3b88adc11e56494aac0254ba15336d3"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b93c9a9d9d948bce1d12f32a5f27b53876e0f42cb4f567b8b3f471caabbde59b"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.27130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongfang Zhao, Haixu Tang, Hang Zhang, Tianhao Mao, Xiaofeng Wang","cross_cats":[],"headline":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T04:40:44Z","title":"A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.27130","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T22:45:00.905965Z","id":"1c88ab24-b03a-4899-b48e-b5588ee8a383","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"AI-generated code in real-world repositories differs from human-written code in complexity, structure, and post-commit evolution.","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.","weakest_assumption":"The detection pipeline that combines heuristic filtering with LLM-based classification accurately identifies AI-generated code at scale with acceptable error rates."}},"verdict_id":"1c88ab24-b03a-4899-b48e-b5588ee8a383"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f2af36c91761acc99457815fe7c848988e78e598009a0b06f2d60717fc70abe1","target":"record","created_at":"2026-07-03T00:16:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e25d66c41cab76f4ecd1f14ed7eb1e322c6beab6199416e3bfa3acd7882e3f50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T04:40:44Z","title_canon_sha256":"0d52eefd37182bd8a6f845fa5627cee2925f7780a002b86b42264fa8a5b8ea4d"},"schema_version":"1.0","source":{"id":"2603.27130","kind":"arxiv","version":3}},"canonical_sha256":"2a5805d3452b3a7dbd655ec84a6ec72a80057f0305b517dcfac4cc1e63691376","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a5805d3452b3a7dbd655ec84a6ec72a80057f0305b517dcfac4cc1e63691376","first_computed_at":"2026-07-03T00:16:53.361014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:16:53.361014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZnHtcOBDHSsTpZVBE8HiVqfuuePgknq7eUEvTiB6+xsmf5EoGHIHQ+ZQudGZLFUncE3Vy677HGATMbD017LpBg==","signature_status":"signed_v1","signed_at":"2026-07-03T00:16:53.361396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.27130","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2af36c91761acc99457815fe7c848988e78e598009a0b06f2d60717fc70abe1","sha256:01f87cf318279441df1dd089fae123818f4ce35a3d8edbbfbba770afa3963b94"],"state_sha256":"82c6c133c32f241a8ad40dc6fc6df53ccee8c3e1f5a322a3675ef0f8d7ce12d2"}