{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S4TFVHNWUP2BMSOJ4HXY4CACEX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"44558fda249dd9d4381a0874bde5a9ca8774ff74d83316281afdef2132ba429a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-28T02:33:07Z","title_canon_sha256":"b973adf6f35bd2c53bc459e7b0872b61c703c458daa2e493d087b1d0f7083108"},"schema_version":"1.0","source":{"id":"2201.11903","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11903","created_at":"2026-07-05T05:32:11Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11903v6","created_at":"2026-07-05T05:32:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11903","created_at":"2026-07-05T05:32:11Z"},{"alias_kind":"pith_short_12","alias_value":"S4TFVHNWUP2B","created_at":"2026-07-05T05:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"S4TFVHNWUP2BMSOJ","created_at":"2026-07-05T05:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"S4TFVHNW","created_at":"2026-07-05T05:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:a70f4bbaf76eea3526e6c7fdc84219fd74cd57661dfaf55e288ea55aa351c838","target":"graph","created_at":"2026-07-05T05:32:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples."}],"snapshot_sha256":"62017840d700a56709ec2533a3fae53fca980a1f57a6890ebe29ec5407864bc2"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.11903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Brian Ichter, Dale Schuurmans, Denny Zhou, Ed Chi, Fei Xia, Jason Wei, Maarten Bosma, Quoc Le, Xuezhi Wang","cross_cats":["cs.AI"],"headline":"Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models"},"references":{"count":86,"internal_anchors":14,"resolved_work":86,"sample":[{"cited_arxiv_id":"2204.01691","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":2019},{"cited_arxiv_id":"","doi":"10.18653/v1/d19-1609","is_internal_anchor":false,"ref_index":3,"title":"Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension","work_id":"c346b2eb-e194-4648-aeee-aa600865fe15","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":2018},{"cited_arxiv_id":"2108.07732","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","year":2021}],"snapshot_sha256":"72f62b9f4a6f48785008da5e6374785cbb2e85f43be22329bec5b8e65889c9a6"},"source":{"id":"2201.11903","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-10T12:49:15.009832Z","id":"6818f78d-2a6e-4a5f-bc52-fd2318df83cb","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"6818f78d-2a6e-4a5f-bc52-fd2318df83cb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c684ea4a37f52ffc19d25fcd111b4b8ad1aa747805b89daf2f5937ee06f216f","target":"record","created_at":"2026-07-05T05:32:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"44558fda249dd9d4381a0874bde5a9ca8774ff74d83316281afdef2132ba429a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-28T02:33:07Z","title_canon_sha256":"b973adf6f35bd2c53bc459e7b0872b61c703c458daa2e493d087b1d0f7083108"},"schema_version":"1.0","source":{"id":"2201.11903","kind":"arxiv","version":6}},"canonical_sha256":"97265a9db6a3f41649c9e1ef8e080225d6c5349d53ccc2e3a4a3db18cf236a9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97265a9db6a3f41649c9e1ef8e080225d6c5349d53ccc2e3a4a3db18cf236a9c","first_computed_at":"2026-07-05T05:32:11.522048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:11.522048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r780IIiT0bF35btoqfCc5dCIpAJJs57DWSyPCpp2Pe3Haaa7Xwn+JqcGLn3VMtIxW+XACVCvvrcvQlqjXfOnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:11.522686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.11903","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c684ea4a37f52ffc19d25fcd111b4b8ad1aa747805b89daf2f5937ee06f216f","sha256:a70f4bbaf76eea3526e6c7fdc84219fd74cd57661dfaf55e288ea55aa351c838"],"state_sha256":"46fc361f07304da642fa6715777bbfaa2e12f05365fb4fee60cc16bff68fb1bf"}