{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A4PTODPVLFR3GBDARDIQB4FT72","short_pith_number":"pith:A4PTODPV","schema_version":"1.0","canonical_sha256":"071f370df55963b3046088d100f0b3fe883a72fa56bc37374efd579d3c74ba4d","source":{"kind":"arxiv","id":"2507.12367","version":2},"attestation_state":"computed","paper":{"title":"GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Antonio Orvieto, Brice Rauby, Diganta Misra, Eilif B. Muller, Irina Rish, Justine Gehring, Massimo Caccia, Muawiz Chaudhary, Nizar Islah, Samira Ebrahimi Kahou, Victor May, Zihan Wang","submitted_at":"2025-07-16T16:10:42Z","abstract_excerpt":"The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent version updates while preserving backward compatibility. While existing code evolution benchmarks provide valuable insights, they typically lack execution-based evaluation for generating code compliant with specific library versions. To address this, we introduce GitChameleon 2.0, a novel, meticulously curated dataset comprising 328 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitCh"},"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":false},"canonical_record":{"source":{"id":"2507.12367","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-16T16:10:42Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"4281f7cd27dc9ed86679141842e1ea3d04f8ee6377949f43a7dfef3ccc553e92","abstract_canon_sha256":"1f8ac3da295483c35fe67913868ee5652850568779574ef87984dd4da9985b8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:56.884356Z","signature_b64":"o7gs7zHpERD8MNI4nOOYBlRuTy4KS7URCJ7uEyBpaqKwlNaRYrqOOEsOu6iXq9cPRuhZR0cVH7K4rT00qtTqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"071f370df55963b3046088d100f0b3fe883a72fa56bc37374efd579d3c74ba4d","last_reissued_at":"2026-07-05T11:40:56.883822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:56.883822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Antonio Orvieto, Brice Rauby, Diganta Misra, Eilif B. Muller, Irina Rish, Justine Gehring, Massimo Caccia, Muawiz Chaudhary, Nizar Islah, Samira Ebrahimi Kahou, Victor May, Zihan Wang","submitted_at":"2025-07-16T16:10:42Z","abstract_excerpt":"The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent version updates while preserving backward compatibility. While existing code evolution benchmarks provide valuable insights, they typically lack execution-based evaluation for generating code compliant with specific library versions. To address this, we introduce GitChameleon 2.0, a novel, meticulously curated dataset comprising 328 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitCh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12367","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.12367/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2507.12367","created_at":"2026-07-05T11:40:56.883884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12367v2","created_at":"2026-07-05T11:40:56.883884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12367","created_at":"2026-07-05T11:40:56.883884+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4PTODPVLFR3","created_at":"2026-07-05T11:40:56.883884+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4PTODPVLFR3GBDA","created_at":"2026-07-05T11:40:56.883884+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4PTODPV","created_at":"2026-07-05T11:40:56.883884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25402","citing_title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01213","citing_title":"RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25402","citing_title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06754","citing_title":"ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09515","citing_title":"When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06754","citing_title":"ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72","json":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72.json","graph_json":"https://pith.science/api/pith-number/A4PTODPVLFR3GBDARDIQB4FT72/graph.json","events_json":"https://pith.science/api/pith-number/A4PTODPVLFR3GBDARDIQB4FT72/events.json","paper":"https://pith.science/paper/A4PTODPV"},"agent_actions":{"view_html":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72","download_json":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72.json","view_paper":"https://pith.science/paper/A4PTODPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12367&json=true","fetch_graph":"https://pith.science/api/pith-number/A4PTODPVLFR3GBDARDIQB4FT72/graph.json","fetch_events":"https://pith.science/api/pith-number/A4PTODPVLFR3GBDARDIQB4FT72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72/action/storage_attestation","attest_author":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72/action/author_attestation","sign_citation":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72/action/citation_signature","submit_replication":"https://pith.science/pith/A4PTODPVLFR3GBDARDIQB4FT72/action/replication_record"}},"created_at":"2026-07-05T11:40:56.883884+00:00","updated_at":"2026-07-05T11:40:56.883884+00:00"}