{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IFFK623LHI6F3QFRFK722PKJIM","short_pith_number":"pith:IFFK623L","schema_version":"1.0","canonical_sha256":"414aaf6b6b3a3c5dc0b12abfad3d49433d91943841d7abe6713ad56507343aa1","source":{"kind":"arxiv","id":"2305.14045","version":2},"attestation_state":"computed","paper":{"title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Doyoung Kim, Jamin Shin, Joel Jang, Minjoon Seo, Se June Joo, Seonghyeon Ye, Seungone Kim","submitted_at":"2023-05-23T13:14:59Z","abstract_excerpt":"Language models (LMs) with less than 100B parameters are known to perform poorly on chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this work, we aim to equip smaller LMs with the step-by-step reasoning capability by instruction tuning with CoT rationales. In order to achieve this goal, we first introduce a new instruction-tuning dataset called the CoT Collection, which augments the existing Flan Collection (including only 9 CoT tasks) with additional 1.84 million rationales across 1,060 tasks. We show that CoT fine-tuning Flan-T5 (3B & 11B) with CoT Col"},"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":"2305.14045","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T13:14:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cbfbb219c8e36775c27816aacf8a8c02239151caaffa5926d347fdb3e3d1ad2f","abstract_canon_sha256":"3ac86654bca52db2c1bc4587f4a0a7cea819b42fe150cd1b126ac9900875f0e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:01.599757Z","signature_b64":"3hWdpmX+msiIlTQkqhtAbJgB38nC28jK/LsOWvqnwW80efld7YOu8IXAn75T6TDQvhG9/rZ1GA8ADcgbsIbzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414aaf6b6b3a3c5dc0b12abfad3d49433d91943841d7abe6713ad56507343aa1","last_reissued_at":"2026-07-05T07:01:01.599329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:01.599329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Doyoung Kim, Jamin Shin, Joel Jang, Minjoon Seo, Se June Joo, Seonghyeon Ye, Seungone Kim","submitted_at":"2023-05-23T13:14:59Z","abstract_excerpt":"Language models (LMs) with less than 100B parameters are known to perform poorly on chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this work, we aim to equip smaller LMs with the step-by-step reasoning capability by instruction tuning with CoT rationales. In order to achieve this goal, we first introduce a new instruction-tuning dataset called the CoT Collection, which augments the existing Flan Collection (including only 9 CoT tasks) with additional 1.84 million rationales across 1,060 tasks. We show that CoT fine-tuning Flan-T5 (3B & 11B) with CoT Col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14045","kind":"arxiv","version":2},"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/2305.14045/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":"2305.14045","created_at":"2026-07-05T07:01:01.599392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14045v2","created_at":"2026-07-05T07:01:01.599392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14045","created_at":"2026-07-05T07:01:01.599392+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFFK623LHI6F","created_at":"2026-07-05T07:01:01.599392+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFFK623LHI6F3QFR","created_at":"2026-07-05T07:01:01.599392+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFFK623L","created_at":"2026-07-05T07:01:01.599392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07603","citing_title":"MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00106","citing_title":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03644","citing_title":"AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":134,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM","json":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM.json","graph_json":"https://pith.science/api/pith-number/IFFK623LHI6F3QFRFK722PKJIM/graph.json","events_json":"https://pith.science/api/pith-number/IFFK623LHI6F3QFRFK722PKJIM/events.json","paper":"https://pith.science/paper/IFFK623L"},"agent_actions":{"view_html":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM","download_json":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM.json","view_paper":"https://pith.science/paper/IFFK623L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14045&json=true","fetch_graph":"https://pith.science/api/pith-number/IFFK623LHI6F3QFRFK722PKJIM/graph.json","fetch_events":"https://pith.science/api/pith-number/IFFK623LHI6F3QFRFK722PKJIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM/action/storage_attestation","attest_author":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM/action/author_attestation","sign_citation":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM/action/citation_signature","submit_replication":"https://pith.science/pith/IFFK623LHI6F3QFRFK722PKJIM/action/replication_record"}},"created_at":"2026-07-05T07:01:01.599392+00:00","updated_at":"2026-07-05T07:01:01.599392+00:00"}