{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X7V3QW7I5REU6LB7JXMHEFMXWU","short_pith_number":"pith:X7V3QW7I","schema_version":"1.0","canonical_sha256":"bfebb85be8ec494f2c3f4dd8721597b509e6ff429715eb8c1e4d76876919e3c0","source":{"kind":"arxiv","id":"2411.15645","version":2},"attestation_state":"computed","paper":{"title":"MC-NEST: Enhancing Mathematical Reasoning in Large Language Models leveraging a Monte Carlo Self-Refine Tree","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farhana Keya, Gollam Rabby, S\\\"oren Auer","submitted_at":"2024-11-23T20:31:58Z","abstract_excerpt":"Mathematical reasoning presents significant challenges for large language models (LLMs). To enhance their capabilities, we propose Monte Carlo Self-Refine Tree (MC-NEST), an extension of Monte Carlo Tree Search that integrates LLM-based self-refinement and self-evaluation for improved decision-making in complex reasoning tasks. MC-NEST balances exploration and exploitation using Upper Confidence Bound (UCT) scores combined with diverse selection policies. Through iterative critique and refinement, LLMs learn to reason more strategically. Empirical results demonstrate that MC-NEST with an impor"},"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":"2411.15645","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-23T20:31:58Z","cross_cats_sorted":[],"title_canon_sha256":"df6b24b36e82941ac3e57f3d8451dac2ce106e0ce55442f906fc87a4da7e95be","abstract_canon_sha256":"c7adb5c11e9346fac0e7e32db9c2ec7e8b5499eac0e8d2fa7207543e6316d2ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:15.873494Z","signature_b64":"+VTMfldUVz/mifEln0/8mBebqv0UBqm6GEI43a17NUc3HnJFqoyiksOXPt7HJ5/36r3CLmMtHSDYcF29T50wDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfebb85be8ec494f2c3f4dd8721597b509e6ff429715eb8c1e4d76876919e3c0","last_reissued_at":"2026-07-05T11:13:15.872950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:15.872950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MC-NEST: Enhancing Mathematical Reasoning in Large Language Models leveraging a Monte Carlo Self-Refine Tree","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farhana Keya, Gollam Rabby, S\\\"oren Auer","submitted_at":"2024-11-23T20:31:58Z","abstract_excerpt":"Mathematical reasoning presents significant challenges for large language models (LLMs). To enhance their capabilities, we propose Monte Carlo Self-Refine Tree (MC-NEST), an extension of Monte Carlo Tree Search that integrates LLM-based self-refinement and self-evaluation for improved decision-making in complex reasoning tasks. MC-NEST balances exploration and exploitation using Upper Confidence Bound (UCT) scores combined with diverse selection policies. Through iterative critique and refinement, LLMs learn to reason more strategically. Empirical results demonstrate that MC-NEST with an impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15645","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/2411.15645/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":"2411.15645","created_at":"2026-07-05T11:13:15.873012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15645v2","created_at":"2026-07-05T11:13:15.873012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15645","created_at":"2026-07-05T11:13:15.873012+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7V3QW7I5REU","created_at":"2026-07-05T11:13:15.873012+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7V3QW7I5REU6LB7","created_at":"2026-07-05T11:13:15.873012+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7V3QW7I","created_at":"2026-07-05T11:13:15.873012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":134,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU","json":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU.json","graph_json":"https://pith.science/api/pith-number/X7V3QW7I5REU6LB7JXMHEFMXWU/graph.json","events_json":"https://pith.science/api/pith-number/X7V3QW7I5REU6LB7JXMHEFMXWU/events.json","paper":"https://pith.science/paper/X7V3QW7I"},"agent_actions":{"view_html":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU","download_json":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU.json","view_paper":"https://pith.science/paper/X7V3QW7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15645&json=true","fetch_graph":"https://pith.science/api/pith-number/X7V3QW7I5REU6LB7JXMHEFMXWU/graph.json","fetch_events":"https://pith.science/api/pith-number/X7V3QW7I5REU6LB7JXMHEFMXWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU/action/storage_attestation","attest_author":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU/action/author_attestation","sign_citation":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU/action/citation_signature","submit_replication":"https://pith.science/pith/X7V3QW7I5REU6LB7JXMHEFMXWU/action/replication_record"}},"created_at":"2026-07-05T11:13:15.873012+00:00","updated_at":"2026-07-05T11:13:15.873012+00:00"}