{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K6PMQB5JSKF7VBXJFKUXCNTR3U","short_pith_number":"pith:K6PMQB5J","schema_version":"1.0","canonical_sha256":"579ec807a9928bfa86e92aa9713671dd1e8108204433249d08d43a72176b39d4","source":{"kind":"arxiv","id":"2506.03921","version":1},"attestation_state":"computed","paper":{"title":"Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jacques Klein, Tegawend\\'e F. Bissyand\\'e, Xunzhu Tang","submitted_at":"2025-06-04T13:13:58Z","abstract_excerpt":"Several closed-source LLMs have consistently outperformed open-source alternatives in program repair tasks, primarily due to their superior reasoning capabilities and extensive pre-training. This paper introduces Repairity, a novel three-stage methodology that significantly narrows this performance gap through reasoning extraction and reinforcement learning. Our approach: (1) systematically filters high-quality reasoning traces from closed-source models using correctness verification, (2) transfers this reasoning knowledge to open-source models via supervised fine-tuning, and (3) develops rein"},"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":"2506.03921","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-04T13:13:58Z","cross_cats_sorted":[],"title_canon_sha256":"f09529c24ecdfed5f9eb73952ff6b98bc92635d207aa8a2da45f98d6ca13f727","abstract_canon_sha256":"fd9f14fb7dc15152e305e30d64a11ecc1ff400d65067cfb427ce13d274ff9a99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:54.132854Z","signature_b64":"2TmjiHl3E3eO42yF1qF8GVvn0s8xHPpDGOBlolKzVt8Cak25ZMOoy+KAKvMTzqJgZ8T7KNuO6gOR/2XqSoFkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"579ec807a9928bfa86e92aa9713671dd1e8108204433249d08d43a72176b39d4","last_reissued_at":"2026-07-05T11:15:54.132499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:54.132499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jacques Klein, Tegawend\\'e F. Bissyand\\'e, Xunzhu Tang","submitted_at":"2025-06-04T13:13:58Z","abstract_excerpt":"Several closed-source LLMs have consistently outperformed open-source alternatives in program repair tasks, primarily due to their superior reasoning capabilities and extensive pre-training. This paper introduces Repairity, a novel three-stage methodology that significantly narrows this performance gap through reasoning extraction and reinforcement learning. Our approach: (1) systematically filters high-quality reasoning traces from closed-source models using correctness verification, (2) transfers this reasoning knowledge to open-source models via supervised fine-tuning, and (3) develops rein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03921","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/2506.03921/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":"2506.03921","created_at":"2026-07-05T11:15:54.132552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03921v1","created_at":"2026-07-05T11:15:54.132552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03921","created_at":"2026-07-05T11:15:54.132552+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6PMQB5JSKF7","created_at":"2026-07-05T11:15:54.132552+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6PMQB5JSKF7VBXJ","created_at":"2026-07-05T11:15:54.132552+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6PMQB5J","created_at":"2026-07-05T11:15:54.132552+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/K6PMQB5JSKF7VBXJFKUXCNTR3U","json":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U.json","graph_json":"https://pith.science/api/pith-number/K6PMQB5JSKF7VBXJFKUXCNTR3U/graph.json","events_json":"https://pith.science/api/pith-number/K6PMQB5JSKF7VBXJFKUXCNTR3U/events.json","paper":"https://pith.science/paper/K6PMQB5J"},"agent_actions":{"view_html":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U","download_json":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U.json","view_paper":"https://pith.science/paper/K6PMQB5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03921&json=true","fetch_graph":"https://pith.science/api/pith-number/K6PMQB5JSKF7VBXJFKUXCNTR3U/graph.json","fetch_events":"https://pith.science/api/pith-number/K6PMQB5JSKF7VBXJFKUXCNTR3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U/action/storage_attestation","attest_author":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U/action/author_attestation","sign_citation":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U/action/citation_signature","submit_replication":"https://pith.science/pith/K6PMQB5JSKF7VBXJFKUXCNTR3U/action/replication_record"}},"created_at":"2026-07-05T11:15:54.132552+00:00","updated_at":"2026-07-05T11:15:54.132552+00:00"}