{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJG7WZRKTNJRAETAEECBV2YUXP","short_pith_number":"pith:ZJG7WZRK","schema_version":"1.0","canonical_sha256":"ca4dfb662a9b5310126021041aeb14bbe79911280cc5bd89c3dc2facacaff789","source":{"kind":"arxiv","id":"2509.01947","version":1},"attestation_state":"computed","paper":{"title":"Automated Repair of C Programs Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fatemeh Ghassemi, Mahdi Farzandway","submitted_at":"2025-09-02T04:34:11Z","abstract_excerpt":"This study explores the potential of Large Language Models (LLMs) in automating the repair of C programs. We present a framework that integrates spectrum-based fault localization (SBFL), runtime feedback, and Chain-of-Thought-structured prompting into an autonomous repair loop. Unlike prior approaches, our method explicitly combines statistical program analysis with LLM reasoning. The iterative repair cycle leverages a structured Chain-of-Thought (CoT) prompting approach, where the model reasons over failing tests, suspicious code regions, and prior patch outcomes, before generating new candid"},"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":"2509.01947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-09-02T04:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"2fe2917aae773acb3bde104c46f3ba2349f0bad02843cf4ca69f8d47238a0456","abstract_canon_sha256":"68eabb90725bc785d7e9899be62387e13fbaca006cb39c39379db60a8147a6d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:52.977154Z","signature_b64":"MbBxj4EwkJwqkI3HQT3p+kwLq7YwXlbC2PRlE5KAaK3LFbznxE/j68Xibdy5BRVcqOEHPmojS887Vaypv6ZODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4dfb662a9b5310126021041aeb14bbe79911280cc5bd89c3dc2facacaff789","last_reissued_at":"2026-07-05T12:03:52.976647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:52.976647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Repair of C Programs Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fatemeh Ghassemi, Mahdi Farzandway","submitted_at":"2025-09-02T04:34:11Z","abstract_excerpt":"This study explores the potential of Large Language Models (LLMs) in automating the repair of C programs. We present a framework that integrates spectrum-based fault localization (SBFL), runtime feedback, and Chain-of-Thought-structured prompting into an autonomous repair loop. Unlike prior approaches, our method explicitly combines statistical program analysis with LLM reasoning. The iterative repair cycle leverages a structured Chain-of-Thought (CoT) prompting approach, where the model reasons over failing tests, suspicious code regions, and prior patch outcomes, before generating new candid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01947","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/2509.01947/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":"2509.01947","created_at":"2026-07-05T12:03:52.976710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01947v1","created_at":"2026-07-05T12:03:52.976710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01947","created_at":"2026-07-05T12:03:52.976710+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJG7WZRKTNJR","created_at":"2026-07-05T12:03:52.976710+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJG7WZRKTNJRAETA","created_at":"2026-07-05T12:03:52.976710+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJG7WZRK","created_at":"2026-07-05T12:03:52.976710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08468","citing_title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17508","citing_title":"Augmenting unit test suites from integration tests","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP","json":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP.json","graph_json":"https://pith.science/api/pith-number/ZJG7WZRKTNJRAETAEECBV2YUXP/graph.json","events_json":"https://pith.science/api/pith-number/ZJG7WZRKTNJRAETAEECBV2YUXP/events.json","paper":"https://pith.science/paper/ZJG7WZRK"},"agent_actions":{"view_html":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP","download_json":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP.json","view_paper":"https://pith.science/paper/ZJG7WZRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01947&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJG7WZRKTNJRAETAEECBV2YUXP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJG7WZRKTNJRAETAEECBV2YUXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP/action/storage_attestation","attest_author":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP/action/author_attestation","sign_citation":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP/action/citation_signature","submit_replication":"https://pith.science/pith/ZJG7WZRKTNJRAETAEECBV2YUXP/action/replication_record"}},"created_at":"2026-07-05T12:03:52.976710+00:00","updated_at":"2026-07-05T12:03:52.976710+00:00"}