{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M7HU2DM6QVGM6W7TN5P64T4ZG7","short_pith_number":"pith:M7HU2DM6","schema_version":"1.0","canonical_sha256":"67cf4d0d9e854ccf5bf36f5fee4f9937c4f2b05b7ccb3e8ba0387b2e887d1c3f","source":{"kind":"arxiv","id":"2309.08589","version":2},"attestation_state":"computed","paper":{"title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"David C. Parkes, Hugh Zhang","submitted_at":"2023-09-15T17:44:17Z","abstract_excerpt":"Large language models have astounded the world with fascinating new capabilities. However, they currently lack the ability to teach themselves new skills, relying instead on large amounts of human-generated training data. We introduce SECToR (Self-Education via Chain-of-Thought Reasoning), a proof-of-concept demonstration that language models can teach themselves new skills using chain-of-thought reasoning. During the self-learning loop, SECToR asks models to solve addition problems using chain-of-thought reasoning before training the next version of the model to solve those same problems dire"},"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":"2309.08589","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:44:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ba9be76b90308700f47ab99d18700fe2d3643f5a83322a988b39ccf0fc22e5f8","abstract_canon_sha256":"b78da450a574a5df313c692501d4705cb17cfada0f6c35d6a6091f25a701b2ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:28.246745Z","signature_b64":"ubG/ccPKfrOWJhQzSn6zkLZQ18nvK0LKTvkL5gZVgfHMCwdJitC6MW1zol/YzQVLb+CX0FmX8oSit3yN63wVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67cf4d0d9e854ccf5bf36f5fee4f9937c4f2b05b7ccb3e8ba0387b2e887d1c3f","last_reissued_at":"2026-07-05T07:10:28.246275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:28.246275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"David C. Parkes, Hugh Zhang","submitted_at":"2023-09-15T17:44:17Z","abstract_excerpt":"Large language models have astounded the world with fascinating new capabilities. However, they currently lack the ability to teach themselves new skills, relying instead on large amounts of human-generated training data. We introduce SECToR (Self-Education via Chain-of-Thought Reasoning), a proof-of-concept demonstration that language models can teach themselves new skills using chain-of-thought reasoning. During the self-learning loop, SECToR asks models to solve addition problems using chain-of-thought reasoning before training the next version of the model to solve those same problems dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08589","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/2309.08589/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":"2309.08589","created_at":"2026-07-05T07:10:28.246344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08589v2","created_at":"2026-07-05T07:10:28.246344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08589","created_at":"2026-07-05T07:10:28.246344+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7HU2DM6QVGM","created_at":"2026-07-05T07:10:28.246344+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7HU2DM6QVGM6W7T","created_at":"2026-07-05T07:10:28.246344+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7HU2DM6","created_at":"2026-07-05T07:10:28.246344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.02079","citing_title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7","json":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7.json","graph_json":"https://pith.science/api/pith-number/M7HU2DM6QVGM6W7TN5P64T4ZG7/graph.json","events_json":"https://pith.science/api/pith-number/M7HU2DM6QVGM6W7TN5P64T4ZG7/events.json","paper":"https://pith.science/paper/M7HU2DM6"},"agent_actions":{"view_html":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7","download_json":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7.json","view_paper":"https://pith.science/paper/M7HU2DM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08589&json=true","fetch_graph":"https://pith.science/api/pith-number/M7HU2DM6QVGM6W7TN5P64T4ZG7/graph.json","fetch_events":"https://pith.science/api/pith-number/M7HU2DM6QVGM6W7TN5P64T4ZG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7/action/storage_attestation","attest_author":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7/action/author_attestation","sign_citation":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7/action/citation_signature","submit_replication":"https://pith.science/pith/M7HU2DM6QVGM6W7TN5P64T4ZG7/action/replication_record"}},"created_at":"2026-07-05T07:10:28.246344+00:00","updated_at":"2026-07-05T07:10:28.246344+00:00"}