{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M7HU2DM6QVGM6W7TN5P64T4ZG7","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":"b78da450a574a5df313c692501d4705cb17cfada0f6c35d6a6091f25a701b2ca","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:44:17Z","title_canon_sha256":"ba9be76b90308700f47ab99d18700fe2d3643f5a83322a988b39ccf0fc22e5f8"},"schema_version":"1.0","source":{"id":"2309.08589","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08589","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08589v2","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08589","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_12","alias_value":"M7HU2DM6QVGM","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_16","alias_value":"M7HU2DM6QVGM6W7T","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_8","alias_value":"M7HU2DM6","created_at":"2026-07-05T07:10:28Z"}],"graph_snapshots":[{"event_id":"sha256:b4b667ffee79b460dd59844e3d1585712d777ded7d5d3e631e2b2c07db417d12","target":"graph","created_at":"2026-07-05T07:10:28Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.08589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David C. Parkes, Hugh Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:44:17Z","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08589","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c0b26dac14c4db442b148609eb2eb5ce1f332473c886ed5bdc02ade1ba14019","target":"record","created_at":"2026-07-05T07:10:28Z","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":"b78da450a574a5df313c692501d4705cb17cfada0f6c35d6a6091f25a701b2ca","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:44:17Z","title_canon_sha256":"ba9be76b90308700f47ab99d18700fe2d3643f5a83322a988b39ccf0fc22e5f8"},"schema_version":"1.0","source":{"id":"2309.08589","kind":"arxiv","version":2}},"canonical_sha256":"67cf4d0d9e854ccf5bf36f5fee4f9937c4f2b05b7ccb3e8ba0387b2e887d1c3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67cf4d0d9e854ccf5bf36f5fee4f9937c4f2b05b7ccb3e8ba0387b2e887d1c3f","first_computed_at":"2026-07-05T07:10:28.246275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:28.246275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ubG/ccPKfrOWJhQzSn6zkLZQ18nvK0LKTvkL5gZVgfHMCwdJitC6MW1zol/YzQVLb+CX0FmX8oSit3yN63wVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:28.246745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08589","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c0b26dac14c4db442b148609eb2eb5ce1f332473c886ed5bdc02ade1ba14019","sha256:b4b667ffee79b460dd59844e3d1585712d777ded7d5d3e631e2b2c07db417d12"],"state_sha256":"e1c88a6bf2d1f6e4992be96532f87dd4ecb836d102a7cef0151534e02236e5d9"}