{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:37763PWRJT5FWWNBCASQQ2G7KF","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":"971dd933114d6f0cb12013e3760a1441e7a2468a748fa35ff1145ae4d5b2973a","cross_cats_sorted":["cs.AI","cs.PL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T15:13:17Z","title_canon_sha256":"8aa8e4fd2fb8010c484eb2ada3fbeff07ee5c21602bba64478ccb16ea2e9e196"},"schema_version":"1.0","source":{"id":"2306.09896","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09896","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09896v5","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09896","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"pith_short_12","alias_value":"37763PWRJT5F","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"pith_short_16","alias_value":"37763PWRJT5FWWNB","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"pith_short_8","alias_value":"37763PWR","created_at":"2026-07-05T07:40:40Z"}],"graph_snapshots":[{"event_id":"sha256:e1bbe3e9b6bd8f15cef25849a90ab8ebcdc9292492cb61dfdc2915323aecd49a","target":"graph","created_at":"2026-07-05T07:40:40Z","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/2306.09896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost performance in these settings. However, despite its increasing popularity, existing studies of self-repair have been limited in scope; in many settings, its efficacy thus remains poorly understood. In this paper, we analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS. We find that when the cost of carrying o","authors_text":"Armando Solar-Lezama, Chenglong Wang, Jeevana Priya Inala, Jianfeng Gao, Theo X. Olausson","cross_cats":["cs.AI","cs.PL","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T15:13:17Z","title":"Is Self-Repair a Silver Bullet for Code Generation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09896","kind":"arxiv","version":5},"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":"sha256:0757cb2dc5cdde9b624d3849cb1e4aa5dcd0c7b6041dee4fa07f2015e7585e3c","target":"record","created_at":"2026-07-05T07:40:40Z","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":"971dd933114d6f0cb12013e3760a1441e7a2468a748fa35ff1145ae4d5b2973a","cross_cats_sorted":["cs.AI","cs.PL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T15:13:17Z","title_canon_sha256":"8aa8e4fd2fb8010c484eb2ada3fbeff07ee5c21602bba64478ccb16ea2e9e196"},"schema_version":"1.0","source":{"id":"2306.09896","kind":"arxiv","version":5}},"canonical_sha256":"dfffedbed14cfa5b59a110250868df516f4b4d26ad19b63d7c1de8473e9dcff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfffedbed14cfa5b59a110250868df516f4b4d26ad19b63d7c1de8473e9dcff3","first_computed_at":"2026-07-05T07:40:40.667454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:40.667454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l13gRcjkbSmS0rrYGN6YdnF0ektHUNIhq8d1uhyh42nQXY4hWluM5U5I7lGUn7s/Gu+8rBXRfMn74FWp2poNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:40.668173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09896","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0757cb2dc5cdde9b624d3849cb1e4aa5dcd0c7b6041dee4fa07f2015e7585e3c","sha256:e1bbe3e9b6bd8f15cef25849a90ab8ebcdc9292492cb61dfdc2915323aecd49a"],"state_sha256":"db399f388b424aef5caa00bee9c37a021db4d61dc0b4f98acf70fb74233d48fa"}