{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:STPRX7EZL6UUFWHOINOPVNZCI6","short_pith_number":"pith:STPRX7EZ","schema_version":"1.0","canonical_sha256":"94df1bfc995fa942d8ee435cfab7224794c0dbef3a32f9019210d976a7a51f94","source":{"kind":"arxiv","id":"2601.23257","version":2},"attestation_state":"computed","paper":{"title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chenglin Li, Shin Hwei Tan, Tse-Hsun (Peter) Chen, Yisen Xu, Zehao Wang","submitted_at":"2026-01-30T18:25:39Z","abstract_excerpt":"Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning independently for each issue, failing to reuse successful patterns from prior repairs, even though real-world repositories contain many related issues with shared structure or constraints. Existing methods typically rely on forward exploration, which operates under outcome uncertainty, incurs substantial inference-time overhead, and can drift from the final correct patch. We propose Conditional Reasoning Distillation (Con"},"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":"2601.23257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-01-30T18:25:39Z","cross_cats_sorted":[],"title_canon_sha256":"eacdcf17c2a9a8633b414b60349905d917dc4d11b9002568254c58254def31b5","abstract_canon_sha256":"ee9f75e10ac1ae84d485aea74a627ab134030fbe9961c63dcbbfbb653c917049"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:02.926038Z","signature_b64":"YyogEtxqP0l6/64m6U+It5JBqsNgjFfr2X5ndql3Nltjp2Cn5P2Kf2/8CvEKTPwrIP7TTQuUuYGw5AJ7NKj4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94df1bfc995fa942d8ee435cfab7224794c0dbef3a32f9019210d976a7a51f94","last_reissued_at":"2026-05-29T01:05:02.925056Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:02.925056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chenglin Li, Shin Hwei Tan, Tse-Hsun (Peter) Chen, Yisen Xu, Zehao Wang","submitted_at":"2026-01-30T18:25:39Z","abstract_excerpt":"Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning independently for each issue, failing to reuse successful patterns from prior repairs, even though real-world repositories contain many related issues with shared structure or constraints. Existing methods typically rely on forward exploration, which operates under outcome uncertainty, incurs substantial inference-time overhead, and can drift from the final correct patch. We propose Conditional Reasoning Distillation (Con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23257","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/2601.23257/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":"2601.23257","created_at":"2026-05-29T01:05:02.925187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23257v2","created_at":"2026-05-29T01:05:02.925187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23257","created_at":"2026-05-29T01:05:02.925187+00:00"},{"alias_kind":"pith_short_12","alias_value":"STPRX7EZL6UU","created_at":"2026-05-29T01:05:02.925187+00:00"},{"alias_kind":"pith_short_16","alias_value":"STPRX7EZL6UUFWHO","created_at":"2026-05-29T01:05:02.925187+00:00"},{"alias_kind":"pith_short_8","alias_value":"STPRX7EZ","created_at":"2026-05-29T01:05:02.925187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07882","citing_title":"Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6","json":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6.json","graph_json":"https://pith.science/api/pith-number/STPRX7EZL6UUFWHOINOPVNZCI6/graph.json","events_json":"https://pith.science/api/pith-number/STPRX7EZL6UUFWHOINOPVNZCI6/events.json","paper":"https://pith.science/paper/STPRX7EZ"},"agent_actions":{"view_html":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6","download_json":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6.json","view_paper":"https://pith.science/paper/STPRX7EZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23257&json=true","fetch_graph":"https://pith.science/api/pith-number/STPRX7EZL6UUFWHOINOPVNZCI6/graph.json","fetch_events":"https://pith.science/api/pith-number/STPRX7EZL6UUFWHOINOPVNZCI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6/action/storage_attestation","attest_author":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6/action/author_attestation","sign_citation":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6/action/citation_signature","submit_replication":"https://pith.science/pith/STPRX7EZL6UUFWHOINOPVNZCI6/action/replication_record"}},"created_at":"2026-05-29T01:05:02.925187+00:00","updated_at":"2026-05-29T01:05:02.925187+00:00"}