{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCTORMDDYCLEXECMJFP3UKIKGT","short_pith_number":"pith:GCTORMDD","schema_version":"1.0","canonical_sha256":"30a6e8b063c0964b904c495fba290a34c073851a0affa4bedc221912544b87da","source":{"kind":"arxiv","id":"2507.15822","version":2},"attestation_state":"computed","paper":{"title":"Do AI models help produce verified bug fixes?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alessandro Schena, Bertrand Meyer, Ilgiz Mustafin, Li Huang, Marco Piccioni, Reto Weber","submitted_at":"2025-07-21T17:30:16Z","abstract_excerpt":"Among areas of software engineering where AI techniques -- particularly, Large Language Models -- seem poised to yield dramatic improvements, an attractive candidate is Automatic Program Repair (APR), the production of satisfactory corrections to software bugs. Does this expectation materialize in practice? How do we find out, making sure that proposed corrections actually work? If programmers have access to LLMs, how do they actually use them to complement their own skills?\n  To answer these questions, we took advantage of the availability of a program-proving environment, which formally dete"},"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":"2507.15822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-21T17:30:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4cf80610b4665d40a01608c521a32a76eeec144ea01f1a1a46b0a5ee256bf22c","abstract_canon_sha256":"81c859f349778a7deebcd658aec4a6d5681da14d00bb66074166913f85cc28be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:05.873477Z","signature_b64":"WCvzL4DuSGu8NgGnO94CLxreQ+uzYbR2N8ivMbqUSzb8Ntfuz4kgp3k2iL5ltVrIgOrp2eE2wZ4nuZGVx7bwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a6e8b063c0964b904c495fba290a34c073851a0affa4bedc221912544b87da","last_reissued_at":"2026-07-05T11:48:05.872868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:05.872868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do AI models help produce verified bug fixes?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alessandro Schena, Bertrand Meyer, Ilgiz Mustafin, Li Huang, Marco Piccioni, Reto Weber","submitted_at":"2025-07-21T17:30:16Z","abstract_excerpt":"Among areas of software engineering where AI techniques -- particularly, Large Language Models -- seem poised to yield dramatic improvements, an attractive candidate is Automatic Program Repair (APR), the production of satisfactory corrections to software bugs. Does this expectation materialize in practice? How do we find out, making sure that proposed corrections actually work? If programmers have access to LLMs, how do they actually use them to complement their own skills?\n  To answer these questions, we took advantage of the availability of a program-proving environment, which formally dete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15822","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/2507.15822/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":"2507.15822","created_at":"2026-07-05T11:48:05.872931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15822v2","created_at":"2026-07-05T11:48:05.872931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15822","created_at":"2026-07-05T11:48:05.872931+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCTORMDDYCLE","created_at":"2026-07-05T11:48:05.872931+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCTORMDDYCLEXECM","created_at":"2026-07-05T11:48:05.872931+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCTORMDD","created_at":"2026-07-05T11:48:05.872931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT","json":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT.json","graph_json":"https://pith.science/api/pith-number/GCTORMDDYCLEXECMJFP3UKIKGT/graph.json","events_json":"https://pith.science/api/pith-number/GCTORMDDYCLEXECMJFP3UKIKGT/events.json","paper":"https://pith.science/paper/GCTORMDD"},"agent_actions":{"view_html":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT","download_json":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT.json","view_paper":"https://pith.science/paper/GCTORMDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15822&json=true","fetch_graph":"https://pith.science/api/pith-number/GCTORMDDYCLEXECMJFP3UKIKGT/graph.json","fetch_events":"https://pith.science/api/pith-number/GCTORMDDYCLEXECMJFP3UKIKGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT/action/storage_attestation","attest_author":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT/action/author_attestation","sign_citation":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT/action/citation_signature","submit_replication":"https://pith.science/pith/GCTORMDDYCLEXECMJFP3UKIKGT/action/replication_record"}},"created_at":"2026-07-05T11:48:05.872931+00:00","updated_at":"2026-07-05T11:48:05.872931+00:00"}