{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XSWWZT3DM7GYNZN2QQO7TK4FSY","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":"a0cefbd684384449c0c6ed530cbe25789673af80092aa39def302eb303b9d082","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-25T15:45:55Z","title_canon_sha256":"bcc72884d14331a1de8658dbdc4e2515dbc77d35eb51903865e023df4273f0ef"},"schema_version":"1.0","source":{"id":"2507.19390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19390","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19390v1","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19390","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"XSWWZT3DM7GY","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"XSWWZT3DM7GYNZN2","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"XSWWZT3D","created_at":"2026-07-05T11:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:179752b1c32a10fb006e778be537d54a6624901390f1a948b54eab5cb7afc37d","target":"graph","created_at":"2026-07-05T11:43:24Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.19390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) for code generation evolve rapidly through fine-tuning, merging, or new model releases. However, such updates can introduce regressions, not only in correctness but also in code quality and performance. To address this, we present ReCatcher, a regression testing framework for Python code generation. ReCatcher systematically compares two LLMs, typically a current model and a candidate update, across three dimensions: logical correctness, static code quality, and execution performance. We apply ReCatcher to assess regressions across three update scenarios, fine-tunin","authors_text":"Altaf Allah Abbassi, Amin Nikanjam, Foutse Khomh, Leuson Da Silva","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-25T15:45:55Z","title":"ReCatcher: Towards LLMs Regression Testing for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19390","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bca3c623033f7dee65b3da0e7f8f63efa3203f62ddcd33491223bc6f69ebf7d1","target":"record","created_at":"2026-07-05T11:43:24Z","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":"a0cefbd684384449c0c6ed530cbe25789673af80092aa39def302eb303b9d082","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-25T15:45:55Z","title_canon_sha256":"bcc72884d14331a1de8658dbdc4e2515dbc77d35eb51903865e023df4273f0ef"},"schema_version":"1.0","source":{"id":"2507.19390","kind":"arxiv","version":1}},"canonical_sha256":"bcad6ccf6367cd86e5ba841df9ab8596232bc2abd382a3749a2ddad8c1794d34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcad6ccf6367cd86e5ba841df9ab8596232bc2abd382a3749a2ddad8c1794d34","first_computed_at":"2026-07-05T11:43:24.783238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:24.783238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U7hp58oUzT9TjdPJgYtL6zANcZgLOEMmn28Vqld+hJJc8qOIETaRaQXS9QRiCVhQIXGSLjJ3ajRQ6/scvEp7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:24.783753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bca3c623033f7dee65b3da0e7f8f63efa3203f62ddcd33491223bc6f69ebf7d1","sha256:179752b1c32a10fb006e778be537d54a6624901390f1a948b54eab5cb7afc37d"],"state_sha256":"f4da0b9698217f7b3bbc79514cf1d56a286afc2ee95cbb729aa7812d88994aff"}