{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OOIW6D7P2P6SYAWF6IWLW6ZI44","short_pith_number":"pith:OOIW6D7P","schema_version":"1.0","canonical_sha256":"73916f0fefd3fd2c02c5f22cbb7b28e72a6d630a8d821461cda07f7142e9b681","source":{"kind":"arxiv","id":"2210.03493","version":1},"attestation_state":"computed","paper":{"title":"Automatic Chain of Thought Prompting in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Smola, Aston Zhang, Mu Li, Zhuosheng Zhang","submitted_at":"2022-10-07T12:28:21Z","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"},"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":true},"canonical_record":{"source":{"id":"2210.03493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T12:28:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3abecc45e8f72884c7d98a88e67f227a9e9be1b2961d12479cbdf99082dd4715","abstract_canon_sha256":"899052b0b951193f4702fba551d1dad6445035f19118485fbbf21ea5a65f64be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.161562Z","signature_b64":"dgJ04dfyIEKx84jJKquuPo5fz2r+xVUgyccF3xfAq2YWsHK4qeoGOAELmDpilJxj/EGNdSD4bN8AfSeSOxcmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73916f0fefd3fd2c02c5f22cbb7b28e72a6d630a8d821461cda07f7142e9b681","last_reissued_at":"2026-05-17T23:38:48.161086Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.161086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Chain of Thought Prompting in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Smola, Aston Zhang, Mu Li, Zhuosheng Zhang","submitted_at":"2022-10-07T12:28:21Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cea6e5c124e2dcbc535f9263c4e4a453347065e437d52df520d603ce4583d9c6"},"source":{"id":"2210.03493","kind":"arxiv","version":1},"verdict":{"id":"e1a81ef3-4178-4b0a-84b8-815962e157cb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T10:36:28.283141Z","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.","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","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.","pith_extraction_headline":"Auto-CoT lets large language models build their own chain-of-thought demonstrations by sampling diverse questions."},"references":{"count":32,"sample":[{"doi":"","year":2020,"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","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"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","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","ref_index":3,"cited_arxiv_id":"2201.08239","is_internal_anchor":true},{"doi":"","year":2022,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","ref_index":4,"cited_arxiv_id":"2204.02311","is_internal_anchor":true},{"doi":"","year":2015,"title":"Large Language Models are Zero-Shot Reasoners","work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","ref_index":5,"cited_arxiv_id":"2205.11916","is_internal_anchor":true}],"resolved_work":32,"snapshot_sha256":"323120ad02d5c17afc6ed77ac6b4421920cf17d34a81eee88a9da8fecae6eeaa","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ec72543635480f50d3fd7491dbea7a0e7fd313f0a45881f501daffe1ce5fda2c"},"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":"2210.03493","created_at":"2026-05-17T23:38:48.161161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03493v1","created_at":"2026-05-17T23:38:48.161161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03493","created_at":"2026-05-17T23:38:48.161161+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOIW6D7P2P6S","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOIW6D7P2P6SYAWF","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOIW6D7P","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":37,"internal_anchor_count":37,"sample":[{"citing_arxiv_id":"2409.11022","citing_title":"DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05664","citing_title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21856","citing_title":"The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17088","citing_title":"ACIL: Auto Chain of Thoughts for In-Context Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2506.13351","citing_title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":144,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":145,"is_internal_anchor":true},{"citing_arxiv_id":"2509.25699","citing_title":"AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.15946","citing_title":"Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2510.08804","citing_title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2511.01188","citing_title":"ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15436","citing_title":"Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2406.04692","citing_title":"Mixture-of-Agents Enhances Large Language Model Capabilities","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2303.09014","citing_title":"ART: Automatic multi-step reasoning and tool-use for large language models","ref_index":145,"is_internal_anchor":true},{"citing_arxiv_id":"2512.24329","citing_title":"World model inspired sarcasm reasoning with large language model agents","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2601.06993","citing_title":"Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2304.06364","citing_title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":186,"is_internal_anchor":true},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":191,"is_internal_anchor":true},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2603.10477","citing_title":"PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13037","citing_title":"MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2305.19118","citing_title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","ref_index":82,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44","json":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44.json","graph_json":"https://pith.science/api/pith-number/OOIW6D7P2P6SYAWF6IWLW6ZI44/graph.json","events_json":"https://pith.science/api/pith-number/OOIW6D7P2P6SYAWF6IWLW6ZI44/events.json","paper":"https://pith.science/paper/OOIW6D7P"},"agent_actions":{"view_html":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44","download_json":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44.json","view_paper":"https://pith.science/paper/OOIW6D7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03493&json=true","fetch_graph":"https://pith.science/api/pith-number/OOIW6D7P2P6SYAWF6IWLW6ZI44/graph.json","fetch_events":"https://pith.science/api/pith-number/OOIW6D7P2P6SYAWF6IWLW6ZI44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44/action/storage_attestation","attest_author":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44/action/author_attestation","sign_citation":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44/action/citation_signature","submit_replication":"https://pith.science/pith/OOIW6D7P2P6SYAWF6IWLW6ZI44/action/replication_record"}},"created_at":"2026-05-17T23:38:48.161161+00:00","updated_at":"2026-05-17T23:38:48.161161+00:00"}