{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S4TFVHNWUP2BMSOJ4HXY4CACEX","short_pith_number":"pith:S4TFVHNW","schema_version":"1.0","canonical_sha256":"97265a9db6a3f41649c9e1ef8e080225d6c5349d53ccc2e3a4a3db18cf236a9c","source":{"kind":"arxiv","id":"2201.11903","version":6},"attestation_state":"computed","paper":{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Brian Ichter, Dale Schuurmans, Denny Zhou, Ed Chi, Fei Xia, Jason Wei, Maarten Bosma, Quoc Le, Xuezhi Wang","submitted_at":"2022-01-28T02:33:07Z","abstract_excerpt":"We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. 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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.11903","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-28T02:33:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b973adf6f35bd2c53bc459e7b0872b61c703c458daa2e493d087b1d0f7083108","abstract_canon_sha256":"44558fda249dd9d4381a0874bde5a9ca8774ff74d83316281afdef2132ba429a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:11.522686Z","signature_b64":"r780IIiT0bF35btoqfCc5dCIpAJJs57DWSyPCpp2Pe3Haaa7Xwn+JqcGLn3VMtIxW+XACVCvvrcvQlqjXfOnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97265a9db6a3f41649c9e1ef8e080225d6c5349d53ccc2e3a4a3db18cf236a9c","last_reissued_at":"2026-07-05T05:32:11.522048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:11.522048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Brian Ichter, Dale Schuurmans, Denny Zhou, Ed Chi, Fei Xia, Jason Wei, Maarten Bosma, Quoc Le, Xuezhi Wang","submitted_at":"2022-01-28T02:33:07Z","abstract_excerpt":"We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. Th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the performance gains are caused by the explicit reasoning steps rather than simply by providing longer or more detailed prompts; the paper compares against standard few-shot prompting but does not exhaustively rule out all alternative explanations for the improvement.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"62017840d700a56709ec2533a3fae53fca980a1f57a6890ebe29ec5407864bc2"},"source":{"id":"2201.11903","kind":"arxiv","version":6},"verdict":{"id":"6818f78d-2a6e-4a5f-bc52-fd2318df83cb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T12:49:15.009832Z","strongest_claim":"prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.","one_line_summary":"Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the performance gains are caused by the explicit reasoning steps rather than simply by providing longer or more detailed prompts; the paper compares against standard few-shot prompting but does not exhaustively rule out all alternative explanations for the improvement.","pith_extraction_headline":"Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.11903/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":86,"sample":[{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":2019,"title":"Aida Amini, Saadia Gabriel, Shanchuan Lin, Rik Koncel-Kedziorski, Yejin Choi, and Hannaneh Hajishirzi. 2019. https://aclanthology.org/N19-1245 M ath QA : Towards interpretable math word problem solvin","work_id":"52727e9e-5988-4c18-9609-e3b38dfb0d99","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/d19-1609","year":2019,"title":"Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension","work_id":"c346b2eb-e194-4648-aeee-aa600865fe15","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Jacob Andreas, Dan Klein, and Sergey Levine. 2018. https://aclanthology.org/N18-1197 Learning with latent language . NAACL","work_id":"f64450f7-143b-4001-8a7f-a8f6f9c4a58e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","ref_index":5,"cited_arxiv_id":"2108.07732","is_internal_anchor":true}],"resolved_work":86,"snapshot_sha256":"72f62b9f4a6f48785008da5e6374785cbb2e85f43be22329bec5b8e65889c9a6","internal_anchors":14},"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":"2201.11903","created_at":"2026-07-05T05:32:11.522119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11903v6","created_at":"2026-07-05T05:32:11.522119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11903","created_at":"2026-07-05T05:32:11.522119+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4TFVHNWUP2B","created_at":"2026-07-05T05:32:11.522119+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4TFVHNWUP2BMSOJ","created_at":"2026-07-05T05:32:11.522119+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4TFVHNW","created_at":"2026-07-05T05:32:11.522119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":370,"internal_anchor_count":370,"sample":[{"citing_arxiv_id":"2604.20316","citing_title":"R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25489","citing_title":"When LLM Rationales Become User-Facing: Effects on Trust Perception, Decision-Making, and Gaze Behaviors","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25445","citing_title":"C3-Bench: A Context-Aware Change Captioning Benchmark","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24747","citing_title":"Scaling Laws for Task-Specific LLM Distillation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24233","citing_title":"Latent Visual States for Efficient Multimodal Reasoning","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26749","citing_title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","ref_index":141,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24937","citing_title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","ref_index":132,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23419","citing_title":"GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22798","citing_title":"Does the Same Token Mean the Same State? MoE Routing as Signal for Reasoning Control","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22862","citing_title":"Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22610","citing_title":"PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22151","citing_title":"Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22179","citing_title":"The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21884","citing_title":"A Verifiable Search Is Not a Learnable Chain-of-Thought","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21678","citing_title":"Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18648","citing_title":"Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19409","citing_title":"OpenRath: Session-Centered Runtime State for Agent Systems","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18065","citing_title":"Intelligence Entropy Principle and the ADE Stability Engineering Framework","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17721","citing_title":"Understanding and Debugging Failures in N-Gram-Based Generative Retrieval","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17819","citing_title":"A Framework for Evaluating Agentic Skills at Scale","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01440","citing_title":"FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18431","citing_title":"Beyond Prediction: Tail-Aware Scheduling for LLM Inference","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17454","citing_title":"Dissecting model behavior through agent trajectories","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13643","citing_title":"Recursive Agent Harnesses","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX","json":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX.json","graph_json":"https://pith.science/api/pith-number/S4TFVHNWUP2BMSOJ4HXY4CACEX/graph.json","events_json":"https://pith.science/api/pith-number/S4TFVHNWUP2BMSOJ4HXY4CACEX/events.json","paper":"https://pith.science/paper/S4TFVHNW"},"agent_actions":{"view_html":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX","download_json":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX.json","view_paper":"https://pith.science/paper/S4TFVHNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11903&json=true","fetch_graph":"https://pith.science/api/pith-number/S4TFVHNWUP2BMSOJ4HXY4CACEX/graph.json","fetch_events":"https://pith.science/api/pith-number/S4TFVHNWUP2BMSOJ4HXY4CACEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX/action/storage_attestation","attest_author":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX/action/author_attestation","sign_citation":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX/action/citation_signature","submit_replication":"https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX/action/replication_record"}},"created_at":"2026-07-05T05:32:11.522119+00:00","updated_at":"2026-07-05T05:32:11.522119+00:00"}