{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P7TGSPF2C35BNWI53OOGY55JAV","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":"0442afcbeb9a84dd7177d33ba8aa3baf9502d7eb4d144384f77ed110bc659602","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-12T10:03:58Z","title_canon_sha256":"d62bdda647081ead65904d292bef824a4a4cb34c83e59623a0d875fb32227c73"},"schema_version":"1.0","source":{"id":"2503.09217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09217","created_at":"2026-07-05T10:29:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09217v1","created_at":"2026-07-05T10:29:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09217","created_at":"2026-07-05T10:29:51Z"},{"alias_kind":"pith_short_12","alias_value":"P7TGSPF2C35B","created_at":"2026-07-05T10:29:51Z"},{"alias_kind":"pith_short_16","alias_value":"P7TGSPF2C35BNWI5","created_at":"2026-07-05T10:29:51Z"},{"alias_kind":"pith_short_8","alias_value":"P7TGSPF2","created_at":"2026-07-05T10:29:51Z"}],"graph_snapshots":[{"event_id":"sha256:e03a19ebf6ef2d26d38889affbfe0dccba8af587560a46f914aaa16d5d13779c","target":"graph","created_at":"2026-07-05T10:29:51Z","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/2503.09217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known datasets like Defects4J, raising questions about their effectiveness on new datasets. In this study, we evaluate 11 top-performing LLMs on DEFECTS4J-TRANS, a new dataset derived from transforming Defects4J while maintaining the original semantics. Results from experiments on both Defects4J and DEFECTS4J-TRANS show that all studied LLMs have limited generalizability in APR tasks, with the average number of correct and ","authors_text":"Fengjie Li, Hongyu Zhang, Jiajun Jiang, Jiajun Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-12T10:03:58Z","title":"Evaluating the Generalizability of LLMs in Automated Program Repair"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09217","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:eb7fa93d88dab797347ac8e3992a59a00a4ee2b6fbc9e0f7b11785f97eb4c178","target":"record","created_at":"2026-07-05T10:29:51Z","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":"0442afcbeb9a84dd7177d33ba8aa3baf9502d7eb4d144384f77ed110bc659602","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-12T10:03:58Z","title_canon_sha256":"d62bdda647081ead65904d292bef824a4a4cb34c83e59623a0d875fb32227c73"},"schema_version":"1.0","source":{"id":"2503.09217","kind":"arxiv","version":1}},"canonical_sha256":"7fe6693cba16fa16d91ddb9c6c77a9055fc49822a8adc3df0ca094c2364ee785","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fe6693cba16fa16d91ddb9c6c77a9055fc49822a8adc3df0ca094c2364ee785","first_computed_at":"2026-07-05T10:29:51.854046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:51.854046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iLVgf7TwFpkyYdsioNsrmS8QmljyZ1I5wS3JeMZynuBOrd0XOsRLz7eVBxziDutveZf/NiRX/ifPquNqM/ksBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:51.854972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb7fa93d88dab797347ac8e3992a59a00a4ee2b6fbc9e0f7b11785f97eb4c178","sha256:e03a19ebf6ef2d26d38889affbfe0dccba8af587560a46f914aaa16d5d13779c"],"state_sha256":"f0445b98e669345b3edb6f60f6bcbd4ff88c3d022a24950451cf24acc46b383b"}