{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YISOHLK5LPX6TWUTLFJZTIGRKQ","short_pith_number":"pith:YISOHLK5","schema_version":"1.0","canonical_sha256":"c224e3ad5d5befe9da93595399a0d154188daacdc1836886fba885fd89bf095f","source":{"kind":"arxiv","id":"2506.12728","version":1},"attestation_state":"computed","paper":{"title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hai Yu, Yibo Wang, Ying Wang, Zhao Wei, Zhihao Peng, Zhiliang Zhu","submitted_at":"2025-06-15T05:42:01Z","abstract_excerpt":"LLMs demonstrate strong performance in auto-mated software engineering, particularly for code generation and issue resolution. While proprietary models like GPT-4o achieve high benchmarks scores on SWE-bench, their API dependence, cost, and privacy concerns limit adoption. Open-source alternatives offer transparency but underperform in complex tasks, especially sub-100B parameter models. Although quality Chain-of-Thought (CoT) data can enhance reasoning, current methods face two critical flaws: (1) weak rejection sampling reduces data quality, and (2) inadequate step validation causes error ac"},"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":"2506.12728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-15T05:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"5a439a22deb81f94e5b406cfc820a5fb592bcd3aa0078174647ecbe58341dd0c","abstract_canon_sha256":"096cd4c270956e19c5f567da312be5f1adb9ce6a42f2ef679640990c0329033b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:58.455515Z","signature_b64":"QZ+q92vQoRIfCyj4aGytZhwovoW1JbWnmHWM02XTR2W0JY/uWcBojRLlyygj/chfxJ35RnnDnpLF4gZSQ4AKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c224e3ad5d5befe9da93595399a0d154188daacdc1836886fba885fd89bf095f","last_reissued_at":"2026-07-05T11:21:58.455032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:58.455032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hai Yu, Yibo Wang, Ying Wang, Zhao Wei, Zhihao Peng, Zhiliang Zhu","submitted_at":"2025-06-15T05:42:01Z","abstract_excerpt":"LLMs demonstrate strong performance in auto-mated software engineering, particularly for code generation and issue resolution. While proprietary models like GPT-4o achieve high benchmarks scores on SWE-bench, their API dependence, cost, and privacy concerns limit adoption. Open-source alternatives offer transparency but underperform in complex tasks, especially sub-100B parameter models. Although quality Chain-of-Thought (CoT) data can enhance reasoning, current methods face two critical flaws: (1) weak rejection sampling reduces data quality, and (2) inadequate step validation causes error ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12728","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/2506.12728/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":"2506.12728","created_at":"2026-07-05T11:21:58.455090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12728v1","created_at":"2026-07-05T11:21:58.455090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12728","created_at":"2026-07-05T11:21:58.455090+00:00"},{"alias_kind":"pith_short_12","alias_value":"YISOHLK5LPX6","created_at":"2026-07-05T11:21:58.455090+00:00"},{"alias_kind":"pith_short_16","alias_value":"YISOHLK5LPX6TWUT","created_at":"2026-07-05T11:21:58.455090+00:00"},{"alias_kind":"pith_short_8","alias_value":"YISOHLK5","created_at":"2026-07-05T11:21:58.455090+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/YISOHLK5LPX6TWUTLFJZTIGRKQ","json":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ.json","graph_json":"https://pith.science/api/pith-number/YISOHLK5LPX6TWUTLFJZTIGRKQ/graph.json","events_json":"https://pith.science/api/pith-number/YISOHLK5LPX6TWUTLFJZTIGRKQ/events.json","paper":"https://pith.science/paper/YISOHLK5"},"agent_actions":{"view_html":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ","download_json":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ.json","view_paper":"https://pith.science/paper/YISOHLK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12728&json=true","fetch_graph":"https://pith.science/api/pith-number/YISOHLK5LPX6TWUTLFJZTIGRKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YISOHLK5LPX6TWUTLFJZTIGRKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/action/storage_attestation","attest_author":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/action/author_attestation","sign_citation":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/action/citation_signature","submit_replication":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/action/replication_record"}},"created_at":"2026-07-05T11:21:58.455090+00:00","updated_at":"2026-07-05T11:21:58.455090+00:00"}