{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MDFLHIBEIAKGR53YFZDDWVDWJG","short_pith_number":"pith:MDFLHIBE","schema_version":"1.0","canonical_sha256":"60cab3a024401468f7782e463b54764992595e1bd9a4a6f0a03761a7d15a2709","source":{"kind":"arxiv","id":"2308.00436","version":3},"attestation_state":"computed","paper":{"title":"SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ning Miao, Tom Rainforth, Yee Whye Teh","submitted_at":"2023-08-01T10:31:36Z","abstract_excerpt":"The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems that require non-linear thinking, even the strongest LLMs make mistakes. To address this, we explore whether LLMs are able to recognize errors in their own step-by-step reasoning, without resorting to external resources. To this end, we propose SelfCheck, a general-purpose zero-shot verification schema for recognizing such errors. We then use the results of th"},"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":"2308.00436","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-01T10:31:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"dbfa322656d1999be0c3d8866c75779fdef95a46de14cd4c495492a6b3643b4a","abstract_canon_sha256":"20863e1c26b0071223eebea3c4373ba8cb4c8d0cd1885eaf9844d86435c1e577"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:25.062502Z","signature_b64":"U1qWbjMj/vjpGpeIi8VB13wxe3LPHrsgx4lzCvyA+Nms404P5lzM6DbbLZEAiA8jiSwb0yWsTF2AtH4jjvrdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60cab3a024401468f7782e463b54764992595e1bd9a4a6f0a03761a7d15a2709","last_reissued_at":"2026-07-05T06:57:25.062101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:25.062101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ning Miao, Tom Rainforth, Yee Whye Teh","submitted_at":"2023-08-01T10:31:36Z","abstract_excerpt":"The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems that require non-linear thinking, even the strongest LLMs make mistakes. To address this, we explore whether LLMs are able to recognize errors in their own step-by-step reasoning, without resorting to external resources. To this end, we propose SelfCheck, a general-purpose zero-shot verification schema for recognizing such errors. We then use the results of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00436","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/2308.00436/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":"2308.00436","created_at":"2026-07-05T06:57:25.062156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.00436v3","created_at":"2026-07-05T06:57:25.062156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00436","created_at":"2026-07-05T06:57:25.062156+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDFLHIBEIAKG","created_at":"2026-07-05T06:57:25.062156+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDFLHIBEIAKGR53Y","created_at":"2026-07-05T06:57:25.062156+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDFLHIBE","created_at":"2026-07-05T06:57:25.062156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30961","citing_title":"EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00726","citing_title":"Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2309.11495","citing_title":"Chain-of-Verification Reduces Hallucination in Large Language Models","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08715","citing_title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12384","citing_title":"Scalable Token-Level Hallucination Detection in Large Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":222,"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":225,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08715","citing_title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03950","citing_title":"UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01474","citing_title":"ReMedi: Reasoner for Medical Clinical Prediction","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":193,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG","json":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG.json","graph_json":"https://pith.science/api/pith-number/MDFLHIBEIAKGR53YFZDDWVDWJG/graph.json","events_json":"https://pith.science/api/pith-number/MDFLHIBEIAKGR53YFZDDWVDWJG/events.json","paper":"https://pith.science/paper/MDFLHIBE"},"agent_actions":{"view_html":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG","download_json":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG.json","view_paper":"https://pith.science/paper/MDFLHIBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.00436&json=true","fetch_graph":"https://pith.science/api/pith-number/MDFLHIBEIAKGR53YFZDDWVDWJG/graph.json","fetch_events":"https://pith.science/api/pith-number/MDFLHIBEIAKGR53YFZDDWVDWJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG/action/storage_attestation","attest_author":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG/action/author_attestation","sign_citation":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG/action/citation_signature","submit_replication":"https://pith.science/pith/MDFLHIBEIAKGR53YFZDDWVDWJG/action/replication_record"}},"created_at":"2026-07-05T06:57:25.062156+00:00","updated_at":"2026-07-05T06:57:25.062156+00:00"}