{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MWTT4MTEOLNVDP6ABJLMQAFHVU","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":"8d5a956deb1ad4b039af7a6c3e0c070439d0da6de56fe16ffb8b897d56aa317d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T18:12:29Z","title_canon_sha256":"6173005dcd10a161020ae69b33f14224c4aaff5d6d49e771be18777ef26d77da"},"schema_version":"1.0","source":{"id":"2410.02884","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02884","created_at":"2026-07-05T09:38:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02884v2","created_at":"2026-07-05T09:38:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02884","created_at":"2026-07-05T09:38:30Z"},{"alias_kind":"pith_short_12","alias_value":"MWTT4MTEOLNV","created_at":"2026-07-05T09:38:30Z"},{"alias_kind":"pith_short_16","alias_value":"MWTT4MTEOLNVDP6A","created_at":"2026-07-05T09:38:30Z"},{"alias_kind":"pith_short_8","alias_value":"MWTT4MTE","created_at":"2026-07-05T09:38:30Z"}],"graph_snapshots":[{"event_id":"sha256:d3c5ae5750395216eee545e21463c3e4b9700765e8573186b916eb846dbab344","target":"graph","created_at":"2026-07-05T09:38:30Z","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/2410.02884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an advanced mathematical problem-solving framework, LLaMA-Berry, for enhancing the mathematical reasoning ability of Large Language Models (LLMs). The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path and utilizes a pairwise reward model to evaluate different paths globally. By leveraging the self-critic and rewriting capabilities of LLMs, Self-Refine applied to MCTS (SR-MCTS) overcomes the inefficiencies and limitations of conventional step-wise and greedy search algorithms by fostering a more efficient exploration ","authors_text":"Di Zhang, Dongzhan Zhou, Jianbo Wu, Jiatong Li, Jingdi Lei, Marco Pavone, Shufei Zhang, Tong Che, Tong Xie, Wanli Ouyang, Xiaoshui Huang, Yuqiang Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T18:12:29Z","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02884","kind":"arxiv","version":2},"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":"sha256:5f4a3c0a8f943b44ea55f9f77fd7616da5e817f237d174fa8d4d350dbcafc11a","target":"record","created_at":"2026-07-05T09:38:30Z","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":"8d5a956deb1ad4b039af7a6c3e0c070439d0da6de56fe16ffb8b897d56aa317d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T18:12:29Z","title_canon_sha256":"6173005dcd10a161020ae69b33f14224c4aaff5d6d49e771be18777ef26d77da"},"schema_version":"1.0","source":{"id":"2410.02884","kind":"arxiv","version":2}},"canonical_sha256":"65a73e326472db51bfc00a56c800a7ad167ca397e120fc78e82f44cca1d32692","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65a73e326472db51bfc00a56c800a7ad167ca397e120fc78e82f44cca1d32692","first_computed_at":"2026-07-05T09:38:30.238216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:30.238216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vN55svNSIBK+UDrcIG982Jr8xEKu8OfjHdPL2fbJ6nnyIrEAJdfmRHJ+iC9zZqfzRCkymmeQIe6dQfPKKIpoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:30.238881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02884","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f4a3c0a8f943b44ea55f9f77fd7616da5e817f237d174fa8d4d350dbcafc11a","sha256:d3c5ae5750395216eee545e21463c3e4b9700765e8573186b916eb846dbab344"],"state_sha256":"68d3eb62d2b733be7b07c37687910b8f196cfd5afad52148c847ed281c966e5a"}