{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MWTT4MTEOLNVDP6ABJLMQAFHVU","short_pith_number":"pith:MWTT4MTE","schema_version":"1.0","canonical_sha256":"65a73e326472db51bfc00a56c800a7ad167ca397e120fc78e82f44cca1d32692","source":{"kind":"arxiv","id":"2410.02884","version":2},"attestation_state":"computed","paper":{"title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","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","submitted_at":"2024-10-03T18:12:29Z","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 "},"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":"2410.02884","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T18:12:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6173005dcd10a161020ae69b33f14224c4aaff5d6d49e771be18777ef26d77da","abstract_canon_sha256":"8d5a956deb1ad4b039af7a6c3e0c070439d0da6de56fe16ffb8b897d56aa317d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:30.238881Z","signature_b64":"vN55svNSIBK+UDrcIG982Jr8xEKu8OfjHdPL2fbJ6nnyIrEAJdfmRHJ+iC9zZqfzRCkymmeQIe6dQfPKKIpoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65a73e326472db51bfc00a56c800a7ad167ca397e120fc78e82f44cca1d32692","last_reissued_at":"2026-07-05T09:38:30.238216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:30.238216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","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","submitted_at":"2024-10-03T18:12:29Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02884","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/2410.02884/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":"2410.02884","created_at":"2026-07-05T09:38:30.238274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02884v2","created_at":"2026-07-05T09:38:30.238274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02884","created_at":"2026-07-05T09:38:30.238274+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWTT4MTEOLNV","created_at":"2026-07-05T09:38:30.238274+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWTT4MTEOLNVDP6A","created_at":"2026-07-05T09:38:30.238274+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWTT4MTE","created_at":"2026-07-05T09:38:30.238274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24233","citing_title":"Latent Visual States for Efficient Multimodal Reasoning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16549","citing_title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17352","citing_title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09413","citing_title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07600","citing_title":"Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU","json":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU.json","graph_json":"https://pith.science/api/pith-number/MWTT4MTEOLNVDP6ABJLMQAFHVU/graph.json","events_json":"https://pith.science/api/pith-number/MWTT4MTEOLNVDP6ABJLMQAFHVU/events.json","paper":"https://pith.science/paper/MWTT4MTE"},"agent_actions":{"view_html":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU","download_json":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU.json","view_paper":"https://pith.science/paper/MWTT4MTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02884&json=true","fetch_graph":"https://pith.science/api/pith-number/MWTT4MTEOLNVDP6ABJLMQAFHVU/graph.json","fetch_events":"https://pith.science/api/pith-number/MWTT4MTEOLNVDP6ABJLMQAFHVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU/action/storage_attestation","attest_author":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU/action/author_attestation","sign_citation":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU/action/citation_signature","submit_replication":"https://pith.science/pith/MWTT4MTEOLNVDP6ABJLMQAFHVU/action/replication_record"}},"created_at":"2026-07-05T09:38:30.238274+00:00","updated_at":"2026-07-05T09:38:30.238274+00:00"}