{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NBXITZXR645AZSVR4JA56W2MRF","short_pith_number":"pith:NBXITZXR","schema_version":"1.0","canonical_sha256":"686e89e6f1f73a0ccab1e241df5b4c89655d11e9935d911962b61d2ef8e7bd5f","source":{"kind":"arxiv","id":"2407.20898","version":1},"attestation_state":"computed","paper":{"title":"ThinkRepair: Self-Directed Automated Program Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chao Ni, Limin Zeng, Shaohua Wang, Xiaohu Yang, Xin Yin, Zhenhao Li","submitted_at":"2024-07-30T15:17:07Z","abstract_excerpt":"Though many approaches have been proposed for Automated Program Repair (APR) and indeed achieved remarkable performance, they still have limitations in fixing bugs that require analyzing and reasoning about the logic of the buggy program. Recently, large language models (LLMs) instructed by prompt engineering have attracted much attention for their powerful ability to address many kinds of tasks including bug-fixing. However, the quality of the prompt will highly affect the ability of LLMs and manually constructing high-quality prompts is a costly endeavor.\n  To address this limitation, we pro"},"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":"2407.20898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-30T15:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"21d67365a0079d8fdaa87e2c7b2ed3553ce12af9de4cad53f1849f6d368cbced","abstract_canon_sha256":"45bfa41813c5325bb300b339de420913445a9741bc58e00365ae9832b1a40d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:20.222518Z","signature_b64":"39VIjKNnVG6lRRhTtdOd7Qwy/zs2uOjA2Dmr8WYesrDpioSo5GCRGWlpYK0JpVly7auauq62j1EA0hjIIO0YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"686e89e6f1f73a0ccab1e241df5b4c89655d11e9935d911962b61d2ef8e7bd5f","last_reissued_at":"2026-07-05T08:50:20.222097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:20.222097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ThinkRepair: Self-Directed Automated Program Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chao Ni, Limin Zeng, Shaohua Wang, Xiaohu Yang, Xin Yin, Zhenhao Li","submitted_at":"2024-07-30T15:17:07Z","abstract_excerpt":"Though many approaches have been proposed for Automated Program Repair (APR) and indeed achieved remarkable performance, they still have limitations in fixing bugs that require analyzing and reasoning about the logic of the buggy program. Recently, large language models (LLMs) instructed by prompt engineering have attracted much attention for their powerful ability to address many kinds of tasks including bug-fixing. However, the quality of the prompt will highly affect the ability of LLMs and manually constructing high-quality prompts is a costly endeavor.\n  To address this limitation, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20898","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/2407.20898/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":"2407.20898","created_at":"2026-07-05T08:50:20.222153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20898v1","created_at":"2026-07-05T08:50:20.222153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20898","created_at":"2026-07-05T08:50:20.222153+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBXITZXR645A","created_at":"2026-07-05T08:50:20.222153+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBXITZXR645AZSVR","created_at":"2026-07-05T08:50:20.222153+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBXITZXR","created_at":"2026-07-05T08:50:20.222153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03245","citing_title":"FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF","json":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF.json","graph_json":"https://pith.science/api/pith-number/NBXITZXR645AZSVR4JA56W2MRF/graph.json","events_json":"https://pith.science/api/pith-number/NBXITZXR645AZSVR4JA56W2MRF/events.json","paper":"https://pith.science/paper/NBXITZXR"},"agent_actions":{"view_html":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF","download_json":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF.json","view_paper":"https://pith.science/paper/NBXITZXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20898&json=true","fetch_graph":"https://pith.science/api/pith-number/NBXITZXR645AZSVR4JA56W2MRF/graph.json","fetch_events":"https://pith.science/api/pith-number/NBXITZXR645AZSVR4JA56W2MRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF/action/storage_attestation","attest_author":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF/action/author_attestation","sign_citation":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF/action/citation_signature","submit_replication":"https://pith.science/pith/NBXITZXR645AZSVR4JA56W2MRF/action/replication_record"}},"created_at":"2026-07-05T08:50:20.222153+00:00","updated_at":"2026-07-05T08:50:20.222153+00:00"}