{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PVAAGVBN4LVRHEI444CKEBXSAE","short_pith_number":"pith:PVAAGVBN","schema_version":"1.0","canonical_sha256":"7d4003542de2eb13911ce704a206f2012b16400eb625a9b511f13988d1e47111","source":{"kind":"arxiv","id":"2410.01707","version":3},"attestation_state":"computed","paper":{"title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aiwei Liu, Boye Niu, Haotian Xu, Hongzhang Liu, Lijie Wen, Xuming Hu, Xuzheng He, Zitian Gao","submitted_at":"2024-10-02T16:15:31Z","abstract_excerpt":"We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlooked its biggest drawback--slower speed compared to CoT; 2. Previous research mainly used MCTS as a tool for LLM reasoning on various tasks with limited quantitative analysis or ablation studies of its components from reasoning interpretability perspective. 3. The reward model is the most crucial component in MCTS, however previous work has rarely co"},"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":"2410.01707","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T16:15:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c720b7be7157bb9bea8d773f54fb831899bfaf42c505c9ccd5c428c47a4c5e4b","abstract_canon_sha256":"2f1cf3cf9a20c5cb2cb37d62d037c45e2db944bd8cf87e2594a46a138812c60f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:04.734064Z","signature_b64":"HiX6eS0ORDwGg+TG4AnUfCfsduMQMenYkhfK6xeQo4/dqNQZHnvsKsOGWwYl9/wO6EZoTK6IxUyh+PdwtauSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d4003542de2eb13911ce704a206f2012b16400eb625a9b511f13988d1e47111","last_reissued_at":"2026-07-05T09:54:04.733564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:04.733564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aiwei Liu, Boye Niu, Haotian Xu, Hongzhang Liu, Lijie Wen, Xuming Hu, Xuzheng He, Zitian Gao","submitted_at":"2024-10-02T16:15:31Z","abstract_excerpt":"We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlooked its biggest drawback--slower speed compared to CoT; 2. Previous research mainly used MCTS as a tool for LLM reasoning on various tasks with limited quantitative analysis or ablation studies of its components from reasoning interpretability perspective. 3. The reward model is the most crucial component in MCTS, however previous work has rarely co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01707","kind":"arxiv","version":3},"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/2410.01707/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":"2410.01707","created_at":"2026-07-05T09:54:04.733624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01707v3","created_at":"2026-07-05T09:54:04.733624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01707","created_at":"2026-07-05T09:54:04.733624+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVAAGVBN4LVR","created_at":"2026-07-05T09:54:04.733624+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVAAGVBN4LVRHEI4","created_at":"2026-07-05T09:54:04.733624+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVAAGVBN","created_at":"2026-07-05T09:54:04.733624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20599","citing_title":"Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13818","citing_title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08592","citing_title":"Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15353","citing_title":"NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10195","citing_title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01348","citing_title":"Procedural Knowledge at Scale Improves Reasoning","ref_index":6,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":204,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10195","citing_title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14687","citing_title":"M2-PALE: A Framework for Explaining Multi-Agent MCTS--Minimax Hybrids via Process Mining and LLMs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17433","citing_title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE","json":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE.json","graph_json":"https://pith.science/api/pith-number/PVAAGVBN4LVRHEI444CKEBXSAE/graph.json","events_json":"https://pith.science/api/pith-number/PVAAGVBN4LVRHEI444CKEBXSAE/events.json","paper":"https://pith.science/paper/PVAAGVBN"},"agent_actions":{"view_html":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE","download_json":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE.json","view_paper":"https://pith.science/paper/PVAAGVBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01707&json=true","fetch_graph":"https://pith.science/api/pith-number/PVAAGVBN4LVRHEI444CKEBXSAE/graph.json","fetch_events":"https://pith.science/api/pith-number/PVAAGVBN4LVRHEI444CKEBXSAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE/action/storage_attestation","attest_author":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE/action/author_attestation","sign_citation":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE/action/citation_signature","submit_replication":"https://pith.science/pith/PVAAGVBN4LVRHEI444CKEBXSAE/action/replication_record"}},"created_at":"2026-07-05T09:54:04.733624+00:00","updated_at":"2026-07-05T09:54:04.733624+00:00"}