{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XYFEDSJVOIXAFVOBFEG3ASWPVK","short_pith_number":"pith:XYFEDSJV","schema_version":"1.0","canonical_sha256":"be0a41c935722e02d5c1290db04acfaa8c9efc3e206c3f471fe79ed1007aa423","source":{"kind":"arxiv","id":"2406.07394","version":2},"attestation_state":"computed","paper":{"title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Di Zhang, Dongzhan Zhou, Wanli Ouyang, Xiaoshui Huang, Yuqiang Li","submitted_at":"2024-06-11T16:01:07Z","abstract_excerpt":"This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasoning tasks. Addressing the challenges of accuracy and reliability in LLMs, particularly in strategic and mathematical reasoning, MCTSr leverages systematic exploration and heuristic self-refine mechanisms to improve decision-making frameworks within LLMs. The algorithm constructs a Monte Carlo search tree through iterative processes of Selection, self-refine, self-evaluation, and "},"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":"2406.07394","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-11T16:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"c90b30fa4324a8c592be7cd73a67267170c51067d005937b9cdb86c1c3d632b2","abstract_canon_sha256":"15c207aaeab09b62466a5f1df95bc9a2f9a001eaa26d25abafb3ed46e4d1d1df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:16.938890Z","signature_b64":"PHcafUMb6zbqKgA1XwDbebLKxdtVA28V4kAJu9z+3N5iC2/sDyMlBaG2BQXUFUUAN/0DcPp9SiSwXx0o7UT8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be0a41c935722e02d5c1290db04acfaa8c9efc3e206c3f471fe79ed1007aa423","last_reissued_at":"2026-07-05T08:31:16.938395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:16.938395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Di Zhang, Dongzhan Zhou, Wanli Ouyang, Xiaoshui Huang, Yuqiang Li","submitted_at":"2024-06-11T16:01:07Z","abstract_excerpt":"This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasoning tasks. Addressing the challenges of accuracy and reliability in LLMs, particularly in strategic and mathematical reasoning, MCTSr leverages systematic exploration and heuristic self-refine mechanisms to improve decision-making frameworks within LLMs. The algorithm constructs a Monte Carlo search tree through iterative processes of Selection, self-refine, self-evaluation, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07394","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/2406.07394/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":"2406.07394","created_at":"2026-07-05T08:31:16.938464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07394v2","created_at":"2026-07-05T08:31:16.938464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07394","created_at":"2026-07-05T08:31:16.938464+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYFEDSJVOIXA","created_at":"2026-07-05T08:31:16.938464+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYFEDSJVOIXAFVOB","created_at":"2026-07-05T08:31:16.938464+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYFEDSJV","created_at":"2026-07-05T08:31:16.938464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26453","citing_title":"Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26728","citing_title":"Scientific discovery as meta-optimization: a combinatorial optimization case study","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05464","citing_title":"Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05253","citing_title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00955","citing_title":"Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25835","citing_title":"Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25454","citing_title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21619","citing_title":"On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency","ref_index":36,"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":133,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26644","citing_title":"When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00323","citing_title":"Online Self-Calibration Against Hallucination in Vision-Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06914","citing_title":"Regulating Branch Parallelism in LLM Serving","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04386","citing_title":"Automatically Generating Hard Math Problems from Hypothesis-Driven Error Analysis","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14853","citing_title":"Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15709","citing_title":"Bilevel Optimization of Agent Skills via Monte Carlo Tree Search","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK","json":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK.json","graph_json":"https://pith.science/api/pith-number/XYFEDSJVOIXAFVOBFEG3ASWPVK/graph.json","events_json":"https://pith.science/api/pith-number/XYFEDSJVOIXAFVOBFEG3ASWPVK/events.json","paper":"https://pith.science/paper/XYFEDSJV"},"agent_actions":{"view_html":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK","download_json":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK.json","view_paper":"https://pith.science/paper/XYFEDSJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07394&json=true","fetch_graph":"https://pith.science/api/pith-number/XYFEDSJVOIXAFVOBFEG3ASWPVK/graph.json","fetch_events":"https://pith.science/api/pith-number/XYFEDSJVOIXAFVOBFEG3ASWPVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK/action/storage_attestation","attest_author":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK/action/author_attestation","sign_citation":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK/action/citation_signature","submit_replication":"https://pith.science/pith/XYFEDSJVOIXAFVOBFEG3ASWPVK/action/replication_record"}},"created_at":"2026-07-05T08:31:16.938464+00:00","updated_at":"2026-07-05T08:31:16.938464+00:00"}