{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YISOHLK5LPX6TWUTLFJZTIGRKQ","short_pith_number":"pith:YISOHLK5","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"},"canonical_sha256":"c224e3ad5d5befe9da93595399a0d154188daacdc1836886fba885fd89bf095f","source":{"kind":"arxiv","id":"2506.12728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12728","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12728v1","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12728","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"YISOHLK5LPX6","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"YISOHLK5LPX6TWUT","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"YISOHLK5","created_at":"2026-07-05T11:21:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YISOHLK5LPX6TWUTLFJZTIGRKQ","target":"record","payload":{"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"},"canonical_sha256":"c224e3ad5d5befe9da93595399a0d154188daacdc1836886fba885fd89bf095f","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"},"source_kind":"arxiv","source_id":"2506.12728","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Difz1VtLjOskaMRSASLTLHe5G5SaSv+tyyHXRxOU69C0cMWlPVQ7ZCkXKfxvM99foLibxyJQpn1QVHnAau/EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:32:24.184531Z"},"content_sha256":"11740e53917df7d18fcaaa77b2dbc13457bbeb7eba710181290192fa662298a6","schema_version":"1.0","event_id":"sha256:11740e53917df7d18fcaaa77b2dbc13457bbeb7eba710181290192fa662298a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YISOHLK5LPX6TWUTLFJZTIGRKQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m60SJPj4ag5mNEU8g87BfSZioRDydM6jAREKnRcV8leh8qYt+gOLSOSAg34bLOhv2UNIMBIsrXBtPMQO76jKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:32:24.185057Z"},"content_sha256":"1839fe0f8223d9535087c2a6f03ee3dce7ce47de64bbf9f9b3d5629350ade88a","schema_version":"1.0","event_id":"sha256:1839fe0f8223d9535087c2a6f03ee3dce7ce47de64bbf9f9b3d5629350ade88a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/bundle.json","state_url":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T08:32:24Z","links":{"resolver":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ","bundle":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/bundle.json","state":"https://pith.science/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YISOHLK5LPX6TWUTLFJZTIGRKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YISOHLK5LPX6TWUTLFJZTIGRKQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"096cd4c270956e19c5f567da312be5f1adb9ce6a42f2ef679640990c0329033b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-15T05:42:01Z","title_canon_sha256":"5a439a22deb81f94e5b406cfc820a5fb592bcd3aa0078174647ecbe58341dd0c"},"schema_version":"1.0","source":{"id":"2506.12728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12728","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12728v1","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12728","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"YISOHLK5LPX6","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"YISOHLK5LPX6TWUT","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"YISOHLK5","created_at":"2026-07-05T11:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:1839fe0f8223d9535087c2a6f03ee3dce7ce47de64bbf9f9b3d5629350ade88a","target":"graph","created_at":"2026-07-05T11:21:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.12728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hai Yu, Yibo Wang, Ying Wang, Zhao Wei, Zhihao Peng, Zhiliang Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12728","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11740e53917df7d18fcaaa77b2dbc13457bbeb7eba710181290192fa662298a6","target":"record","created_at":"2026-07-05T11:21:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"096cd4c270956e19c5f567da312be5f1adb9ce6a42f2ef679640990c0329033b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-15T05:42:01Z","title_canon_sha256":"5a439a22deb81f94e5b406cfc820a5fb592bcd3aa0078174647ecbe58341dd0c"},"schema_version":"1.0","source":{"id":"2506.12728","kind":"arxiv","version":1}},"canonical_sha256":"c224e3ad5d5befe9da93595399a0d154188daacdc1836886fba885fd89bf095f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c224e3ad5d5befe9da93595399a0d154188daacdc1836886fba885fd89bf095f","first_computed_at":"2026-07-05T11:21:58.455032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:58.455032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QZ+q92vQoRIfCyj4aGytZhwovoW1JbWnmHWM02XTR2W0JY/uWcBojRLlyygj/chfxJ35RnnDnpLF4gZSQ4AKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:58.455515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11740e53917df7d18fcaaa77b2dbc13457bbeb7eba710181290192fa662298a6","sha256:1839fe0f8223d9535087c2a6f03ee3dce7ce47de64bbf9f9b3d5629350ade88a"],"state_sha256":"016f4ae2ebf5d81105e3ead37f9b0e550c5b9f0b9c965020c98506c1b8abbcf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Hdy6dCu0HGCOEDQvlFlLuWQq5NR4zbIU4uU+XQ0fZp0+3oipLgOIAbIrZsUh9CvLb9jZH8PQC+XWyak8irZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:32:24.188967Z","bundle_sha256":"51912ac46ebbf7f4f29e74f9f763bb9bbe80b4a684280136fe42517ebd138fa7"}}