{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WA5LH6OY3O77TPFPA6EF35IQAJ","short_pith_number":"pith:WA5LH6OY","schema_version":"1.0","canonical_sha256":"b03ab3f9d8dbbff9bcaf07885df5100247efc6abb04fff0f8228f8c724ec9042","source":{"kind":"arxiv","id":"2305.00633","version":3},"attestation_state":"computed","paper":{"title":"Self-Evaluation Guided Beam Search for Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Junxian He, Kenji Kawaguchi, Min-Yen Kan, Qizhe Xie, Xu Zhao, Yiran Zhao, Yuxi Xie","submitted_at":"2023-05-01T02:37:59Z","abstract_excerpt":"Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging to elicit accurate final results. To tackle this challenge of uncertainty in multi-step reasoning, we introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of LLMs. We propose a decoding algorithm integrating the self-evaluation guidance via stochastic beam search. The self-evaluation guidance serves as a better-calibra"},"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":"2305.00633","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T02:37:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fbc96d3fa4f5543311152995e83d5517a52aa6f8641c1a1bf5321cf4b7da6937","abstract_canon_sha256":"f99db99f1dc67496df8aaf4fa67d714f96d487ba436a1eaeb54fb7ec12414f85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:08.260877Z","signature_b64":"/eSw87iGkd8HP0cO8sLSz/VxlaTk7P6F+f+ZwM3lkEOKil3zWP4pjB5gWmAZMApQjUCy1Jd72RYIbAGY5LrxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b03ab3f9d8dbbff9bcaf07885df5100247efc6abb04fff0f8228f8c724ec9042","last_reissued_at":"2026-07-05T07:05:08.260303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:08.260303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evaluation Guided Beam Search for Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Junxian He, Kenji Kawaguchi, Min-Yen Kan, Qizhe Xie, Xu Zhao, Yiran Zhao, Yuxi Xie","submitted_at":"2023-05-01T02:37:59Z","abstract_excerpt":"Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging to elicit accurate final results. To tackle this challenge of uncertainty in multi-step reasoning, we introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of LLMs. We propose a decoding algorithm integrating the self-evaluation guidance via stochastic beam search. The self-evaluation guidance serves as a better-calibra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00633","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/2305.00633/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":"2305.00633","created_at":"2026-07-05T07:05:08.260380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00633v3","created_at":"2026-07-05T07:05:08.260380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00633","created_at":"2026-07-05T07:05:08.260380+00:00"},{"alias_kind":"pith_short_12","alias_value":"WA5LH6OY3O77","created_at":"2026-07-05T07:05:08.260380+00:00"},{"alias_kind":"pith_short_16","alias_value":"WA5LH6OY3O77TPFP","created_at":"2026-07-05T07:05:08.260380+00:00"},{"alias_kind":"pith_short_8","alias_value":"WA5LH6OY","created_at":"2026-07-05T07:05:08.260380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.05653","citing_title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2310.04406","citing_title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","ref_index":10,"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":217,"is_internal_anchor":false},{"citing_arxiv_id":"2211.12588","citing_title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2303.11366","citing_title":"Reflexion: Language Agents with Verbal Reinforcement Learning","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ","json":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ.json","graph_json":"https://pith.science/api/pith-number/WA5LH6OY3O77TPFPA6EF35IQAJ/graph.json","events_json":"https://pith.science/api/pith-number/WA5LH6OY3O77TPFPA6EF35IQAJ/events.json","paper":"https://pith.science/paper/WA5LH6OY"},"agent_actions":{"view_html":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ","download_json":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ.json","view_paper":"https://pith.science/paper/WA5LH6OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00633&json=true","fetch_graph":"https://pith.science/api/pith-number/WA5LH6OY3O77TPFPA6EF35IQAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WA5LH6OY3O77TPFPA6EF35IQAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ/action/storage_attestation","attest_author":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ/action/author_attestation","sign_citation":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ/action/citation_signature","submit_replication":"https://pith.science/pith/WA5LH6OY3O77TPFPA6EF35IQAJ/action/replication_record"}},"created_at":"2026-07-05T07:05:08.260380+00:00","updated_at":"2026-07-05T07:05:08.260380+00:00"}