{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OOIW6D7P2P6SYAWF6IWLW6ZI44","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":"899052b0b951193f4702fba551d1dad6445035f19118485fbbf21ea5a65f64be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T12:28:21Z","title_canon_sha256":"3abecc45e8f72884c7d98a88e67f227a9e9be1b2961d12479cbdf99082dd4715"},"schema_version":"1.0","source":{"id":"2210.03493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03493","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03493v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03493","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"OOIW6D7P2P6S","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"OOIW6D7P2P6SYAWF","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"OOIW6D7P","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:b8ecc90fc9ff267d52895b4d860ddbb4975357398fc116f10dae08c38cfa1d4a","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"On ten public benchmark reasoning tasks with GPT-3, Auto-CoT consistently matches or exceeds the performance of the CoT paradigm that requires manual designs of demonstrations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That sampling questions for diversity sufficiently mitigates the impact of occasional errors in the automatically generated reasoning chains, so that the constructed demonstrations remain effective overall."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Auto-CoT automatically builds chain-of-thought demonstrations by sampling diverse questions and letting the LLM generate reasoning chains, matching manual CoT performance on ten reasoning tasks with GPT-3."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions."}],"snapshot_sha256":"cea6e5c124e2dcbc535f9263c4e4a453347065e437d52df520d603ce4583d9c6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ec72543635480f50d3fd7491dbea7a0e7fd313f0a45881f501daffe1ce5fda2c"},"paper":{"abstract_excerpt":"Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One leverages a simple prompt like \"Let's think step by step\" to facilitate step-by-step thinking before answering a question. The other uses a few manual demonstrations one by one, each composed of a question and a reasoning chain that leads to an answer. The superior performance of the second paradigm hinges on the hand-crafting of task-specific demonstration","authors_text":"Alex Smola, Aston Zhang, Mu Li, Zhuosheng Zhang","cross_cats":["cs.AI"],"headline":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T12:28:21Z","title":"Automatic Chain of Thought Prompting in Large Language Models"},"references":{"count":32,"internal_anchors":9,"resolved_work":32,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-V oss, Gretch","work_id":"c8c76fe6-9f18-49cf-b7c5-eb092bf80d60","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"URL https://proceedings.neurips.cc/paper/2020/hash/ 1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html. Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, A","work_id":"546635ca-ac36-4775-b6e0-1a7e0066ad49","year":2020},{"cited_arxiv_id":"2201.08239","doi":"","is_internal_anchor":true,"ref_index":3,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","year":null},{"cited_arxiv_id":"2204.02311","doi":"","is_internal_anchor":true,"ref_index":4,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","year":2022},{"cited_arxiv_id":"2205.11916","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Large Language Models are Zero-Shot Reasoners","work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","year":2015}],"snapshot_sha256":"323120ad02d5c17afc6ed77ac6b4421920cf17d34a81eee88a9da8fecae6eeaa"},"source":{"id":"2210.03493","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T10:36:28.283141Z","id":"e1a81ef3-4178-4b0a-84b8-815962e157cb","model_set":{"reader":"grok-4.3"},"one_line_summary":"Auto-CoT automatically builds chain-of-thought demonstrations by sampling diverse questions and letting the LLM generate reasoning chains, matching manual CoT performance on ten reasoning tasks with GPT-3.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions.","strongest_claim":"On ten public benchmark reasoning tasks with GPT-3, Auto-CoT consistently matches or exceeds the performance of the CoT paradigm that requires manual designs of demonstrations.","weakest_assumption":"That sampling questions for diversity sufficiently mitigates the impact of occasional errors in the automatically generated reasoning chains, so that the constructed demonstrations remain effective overall."}},"verdict_id":"e1a81ef3-4178-4b0a-84b8-815962e157cb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4d4123881e494bdd661618a72f1797a1b8ff7eb71f5a957070ebc2dc473690c9","target":"record","created_at":"2026-05-17T23:38:48Z","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":"899052b0b951193f4702fba551d1dad6445035f19118485fbbf21ea5a65f64be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T12:28:21Z","title_canon_sha256":"3abecc45e8f72884c7d98a88e67f227a9e9be1b2961d12479cbdf99082dd4715"},"schema_version":"1.0","source":{"id":"2210.03493","kind":"arxiv","version":1}},"canonical_sha256":"73916f0fefd3fd2c02c5f22cbb7b28e72a6d630a8d821461cda07f7142e9b681","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73916f0fefd3fd2c02c5f22cbb7b28e72a6d630a8d821461cda07f7142e9b681","first_computed_at":"2026-05-17T23:38:48.161086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.161086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dgJ04dfyIEKx84jJKquuPo5fz2r+xVUgyccF3xfAq2YWsHK4qeoGOAELmDpilJxj/EGNdSD4bN8AfSeSOxcmDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.161562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d4123881e494bdd661618a72f1797a1b8ff7eb71f5a957070ebc2dc473690c9","sha256:b8ecc90fc9ff267d52895b4d860ddbb4975357398fc116f10dae08c38cfa1d4a"],"state_sha256":"17839a355aaf6bf9458b52e7d23b4385d25da37888fcab2ef481c5c4f59985e7"}