{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P2NGYXF64HRSQOEESIZHM76Z57","short_pith_number":"pith:P2NGYXF6","schema_version":"1.0","canonical_sha256":"7e9a6c5cbee1e32838849232767fd9efde616d40d99245b306aa63363b7d304f","source":{"kind":"arxiv","id":"2411.05830","version":1},"attestation_state":"computed","paper":{"title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Diganta Misra, Eilif Muller, Irina Rish, Justine Gehring, Massimo Caccia, Nizar Islah, Terry Yue Zhuo","submitted_at":"2024-11-05T23:34:06Z","abstract_excerpt":"The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions. Existing code completion benchmarks often overlook this dynamic aspect, and the one that does consider it relies on static code prediction tasks without execution-based evaluation, offering a limited perspective on a model's practical usability. To address this gap, we introduce \\textbf{\\GitChameleon{}}, a novel, manually curated dataset comprising 116 Python code completion problems, each con"},"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":"2411.05830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-11-05T23:34:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f17e596b6588bca3aca4dcd62544e665a818ea68942e063065f9d695f37e1973","abstract_canon_sha256":"07bf7c01373bc867c42f5bd1d44f132bd59eb03e4cc5be38c59ed5c8dc22202d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:11.838570Z","signature_b64":"1e0cAJ5BA+HNCveLBo+B7/y1JaZjmKWSwHBUegKwmfn6BpQLBepwn5BomkdOx4yYlbgMPRNoI+ST8xmCXgpDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9a6c5cbee1e32838849232767fd9efde616d40d99245b306aa63363b7d304f","last_reissued_at":"2026-07-05T09:33:11.838027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:11.838027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Diganta Misra, Eilif Muller, Irina Rish, Justine Gehring, Massimo Caccia, Nizar Islah, Terry Yue Zhuo","submitted_at":"2024-11-05T23:34:06Z","abstract_excerpt":"The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions. Existing code completion benchmarks often overlook this dynamic aspect, and the one that does consider it relies on static code prediction tasks without execution-based evaluation, offering a limited perspective on a model's practical usability. To address this gap, we introduce \\textbf{\\GitChameleon{}}, a novel, manually curated dataset comprising 116 Python code completion problems, each con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05830","kind":"arxiv","version":1},"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/2411.05830/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":"2411.05830","created_at":"2026-07-05T09:33:11.838088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05830v1","created_at":"2026-07-05T09:33:11.838088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05830","created_at":"2026-07-05T09:33:11.838088+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2NGYXF64HRS","created_at":"2026-07-05T09:33:11.838088+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2NGYXF64HRSQOEE","created_at":"2026-07-05T09:33:11.838088+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2NGYXF6","created_at":"2026-07-05T09:33:11.838088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03622","citing_title":"Toward Executable Repository-Level Code Generation via Environment Alignment","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06279","citing_title":"Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57","json":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57.json","graph_json":"https://pith.science/api/pith-number/P2NGYXF64HRSQOEESIZHM76Z57/graph.json","events_json":"https://pith.science/api/pith-number/P2NGYXF64HRSQOEESIZHM76Z57/events.json","paper":"https://pith.science/paper/P2NGYXF6"},"agent_actions":{"view_html":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57","download_json":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57.json","view_paper":"https://pith.science/paper/P2NGYXF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05830&json=true","fetch_graph":"https://pith.science/api/pith-number/P2NGYXF64HRSQOEESIZHM76Z57/graph.json","fetch_events":"https://pith.science/api/pith-number/P2NGYXF64HRSQOEESIZHM76Z57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57/action/storage_attestation","attest_author":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57/action/author_attestation","sign_citation":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57/action/citation_signature","submit_replication":"https://pith.science/pith/P2NGYXF64HRSQOEESIZHM76Z57/action/replication_record"}},"created_at":"2026-07-05T09:33:11.838088+00:00","updated_at":"2026-07-05T09:33:11.838088+00:00"}