{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KTJRMGWKHO5ILOEAYDCCMU2KGJ","short_pith_number":"pith:KTJRMGWK","schema_version":"1.0","canonical_sha256":"54d3161aca3bba85b880c0c426534a3246c3d951974f4a8804c5cdcde0fcb2e2","source":{"kind":"arxiv","id":"2507.10103","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Bishenghui Tao, Hanyang Guo, Hong-Ning Dai, Peng Di, Xiaoheng Xie, Yu Zhang, Zibin Zheng","submitted_at":"2025-07-14T09:41:51Z","abstract_excerpt":"Automated Program Repair (APR) is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and learning-based APR methods have demonstrated their effectiveness, their performance was constrained by the defect type of repair, the quality of training data, and the size of model parameters. Recently, Large Language Models (LLMs) combined with Retrieval-Augmented-Generation (RAG) have been increasingly adopted in APR tasks. However, current code LLMs and RAG designs neither fully address code repair tasks nor consider"},"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":"2507.10103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-14T09:41:51Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"90e1317dec7f3ac26f2b4d8a345b757566d2ff80993e2ef03920aac81ec65fff","abstract_canon_sha256":"f788185ef13ca30fee93dc9079cbe016ad74897d2e0ab4f2b9f6cd0eef43de1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:45.091021Z","signature_b64":"AIm9bFlamP4Q6eSFMkH4gwDqakxq/Sv/l9OrhFnwRMaiYAZYsilh+e5KKAaXetabeWXQ3LqYrSHTRULTes9wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d3161aca3bba85b880c0c426534a3246c3d951974f4a8804c5cdcde0fcb2e2","last_reissued_at":"2026-07-05T11:36:45.090480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:45.090480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Bishenghui Tao, Hanyang Guo, Hong-Ning Dai, Peng Di, Xiaoheng Xie, Yu Zhang, Zibin Zheng","submitted_at":"2025-07-14T09:41:51Z","abstract_excerpt":"Automated Program Repair (APR) is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and learning-based APR methods have demonstrated their effectiveness, their performance was constrained by the defect type of repair, the quality of training data, and the size of model parameters. Recently, Large Language Models (LLMs) combined with Retrieval-Augmented-Generation (RAG) have been increasingly adopted in APR tasks. However, current code LLMs and RAG designs neither fully address code repair tasks nor consider"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10103","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/2507.10103/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":"2507.10103","created_at":"2026-07-05T11:36:45.090543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10103v1","created_at":"2026-07-05T11:36:45.090543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10103","created_at":"2026-07-05T11:36:45.090543+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTJRMGWKHO5I","created_at":"2026-07-05T11:36:45.090543+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTJRMGWKHO5ILOEA","created_at":"2026-07-05T11:36:45.090543+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTJRMGWK","created_at":"2026-07-05T11:36:45.090543+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/KTJRMGWKHO5ILOEAYDCCMU2KGJ","json":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ.json","graph_json":"https://pith.science/api/pith-number/KTJRMGWKHO5ILOEAYDCCMU2KGJ/graph.json","events_json":"https://pith.science/api/pith-number/KTJRMGWKHO5ILOEAYDCCMU2KGJ/events.json","paper":"https://pith.science/paper/KTJRMGWK"},"agent_actions":{"view_html":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ","download_json":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ.json","view_paper":"https://pith.science/paper/KTJRMGWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10103&json=true","fetch_graph":"https://pith.science/api/pith-number/KTJRMGWKHO5ILOEAYDCCMU2KGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KTJRMGWKHO5ILOEAYDCCMU2KGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ/action/storage_attestation","attest_author":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ/action/author_attestation","sign_citation":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ/action/citation_signature","submit_replication":"https://pith.science/pith/KTJRMGWKHO5ILOEAYDCCMU2KGJ/action/replication_record"}},"created_at":"2026-07-05T11:36:45.090543+00:00","updated_at":"2026-07-05T11:36:45.090543+00:00"}