{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4UQN2NZOQ6XQYW53RWUNHD7OI4","short_pith_number":"pith:4UQN2NZO","canonical_record":{"source":{"id":"2312.02179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-28T17:47:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f35368f3d3e2d1f91c0cc022633e1142010b06d6a7a79e4c0a7f75f2149344ea","abstract_canon_sha256":"4db5e40569b130518eb7c77063be0742755b4fd91e846d352e49c38e2867f82c"},"schema_version":"1.0"},"canonical_sha256":"e520dd372e87af0c5bbb8da8d38fee470174aaac3e49d96f430232db10c4adfb","source":{"kind":"arxiv","id":"2312.02179","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02179","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02179v1","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02179","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"4UQN2NZOQ6XQ","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"4UQN2NZOQ6XQYW53","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"4UQN2NZO","created_at":"2026-07-05T07:20:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4UQN2NZOQ6XQYW53RWUNHD7OI4","target":"record","payload":{"canonical_record":{"source":{"id":"2312.02179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-28T17:47:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f35368f3d3e2d1f91c0cc022633e1142010b06d6a7a79e4c0a7f75f2149344ea","abstract_canon_sha256":"4db5e40569b130518eb7c77063be0742755b4fd91e846d352e49c38e2867f82c"},"schema_version":"1.0"},"canonical_sha256":"e520dd372e87af0c5bbb8da8d38fee470174aaac3e49d96f430232db10c4adfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:13.872730Z","signature_b64":"/abBzA8GAgR/NuRNjaPYD3GDLBu/zDjtu4TjPUGCNCFqVKX/clzFsQyDpILnBKNBEr982Fnp+J8gF537hWyMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e520dd372e87af0c5bbb8da8d38fee470174aaac3e49d96f430232db10c4adfb","last_reissued_at":"2026-07-05T07:20:13.872221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:13.872221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.02179","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRGG1k64TtesZwAjyQitRe0eMIDphZBzv3b6C+B+eA2Kcz1C+erSL0A1Lj5GTQzUX6XCYdDjqE49UsRkcfKpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:19:56.143618Z"},"content_sha256":"a4141a7c3b3cf31a6511054051ab14297165ca20972bbf873eaf63c1e2d9406c","schema_version":"1.0","event_id":"sha256:a4141a7c3b3cf31a6511054051ab14297165ca20972bbf873eaf63c1e2d9406c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4UQN2NZOQ6XQYW53RWUNHD7OI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Chain-of-Thought via Latent-Variable Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aaron Parisi, Charles Sutton, David Dohan, Du Phan, Matthew D. Hoffman, Pavel Sountsov, Rif A. Saurous, Sharad Vikram, Sholto Douglas, Tuan Anh Le","submitted_at":"2023-11-28T17:47:32Z","abstract_excerpt":"Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can also improve LLMs' performance on a specific task by supervised fine-tuning, i.e., by using gradient ascent on some tunable parameters to maximize the average log-likelihood of correct answers from a labeled training set. Naively combining CoT with supervised tuning requires supervision not just of the correct answers, but also of detailed rationales that lead to those answers; these rationales are expensive to prod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02179","kind":"arxiv","version":1},"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/2312.02179/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftd/Lx4CvUv1jhODKxLPljUz/erq0zB0mb8fw/DvwbC1mx2hAXo8kt/KKLfOZFVV39j7XZFw+AfYOuFOXKXQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:19:56.143966Z"},"content_sha256":"0cc0bb1e442df62647d98efc06274615fb3ba325b09213093c725f08004a589f","schema_version":"1.0","event_id":"sha256:0cc0bb1e442df62647d98efc06274615fb3ba325b09213093c725f08004a589f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4/bundle.json","state_url":"https://pith.science/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T09:19:56Z","links":{"resolver":"https://pith.science/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4","bundle":"https://pith.science/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4/bundle.json","state":"https://pith.science/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4UQN2NZOQ6XQYW53RWUNHD7OI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4UQN2NZOQ6XQYW53RWUNHD7OI4","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":"4db5e40569b130518eb7c77063be0742755b4fd91e846d352e49c38e2867f82c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-28T17:47:32Z","title_canon_sha256":"f35368f3d3e2d1f91c0cc022633e1142010b06d6a7a79e4c0a7f75f2149344ea"},"schema_version":"1.0","source":{"id":"2312.02179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02179","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02179v1","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02179","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"4UQN2NZOQ6XQ","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"4UQN2NZOQ6XQYW53","created_at":"2026-07-05T07:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"4UQN2NZO","created_at":"2026-07-05T07:20:13Z"}],"graph_snapshots":[{"event_id":"sha256:0cc0bb1e442df62647d98efc06274615fb3ba325b09213093c725f08004a589f","target":"graph","created_at":"2026-07-05T07:20:13Z","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/2312.02179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can also improve LLMs' performance on a specific task by supervised fine-tuning, i.e., by using gradient ascent on some tunable parameters to maximize the average log-likelihood of correct answers from a labeled training set. Naively combining CoT with supervised tuning requires supervision not just of the correct answers, but also of detailed rationales that lead to those answers; these rationales are expensive to prod","authors_text":"Aaron Parisi, Charles Sutton, David Dohan, Du Phan, Matthew D. Hoffman, Pavel Sountsov, Rif A. Saurous, Sharad Vikram, Sholto Douglas, Tuan Anh Le","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-28T17:47:32Z","title":"Training Chain-of-Thought via Latent-Variable Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02179","kind":"arxiv","version":1},"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:a4141a7c3b3cf31a6511054051ab14297165ca20972bbf873eaf63c1e2d9406c","target":"record","created_at":"2026-07-05T07:20:13Z","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":"4db5e40569b130518eb7c77063be0742755b4fd91e846d352e49c38e2867f82c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-28T17:47:32Z","title_canon_sha256":"f35368f3d3e2d1f91c0cc022633e1142010b06d6a7a79e4c0a7f75f2149344ea"},"schema_version":"1.0","source":{"id":"2312.02179","kind":"arxiv","version":1}},"canonical_sha256":"e520dd372e87af0c5bbb8da8d38fee470174aaac3e49d96f430232db10c4adfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e520dd372e87af0c5bbb8da8d38fee470174aaac3e49d96f430232db10c4adfb","first_computed_at":"2026-07-05T07:20:13.872221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:13.872221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/abBzA8GAgR/NuRNjaPYD3GDLBu/zDjtu4TjPUGCNCFqVKX/clzFsQyDpILnBKNBEr982Fnp+J8gF537hWyMBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:13.872730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4141a7c3b3cf31a6511054051ab14297165ca20972bbf873eaf63c1e2d9406c","sha256:0cc0bb1e442df62647d98efc06274615fb3ba325b09213093c725f08004a589f"],"state_sha256":"937d65687ac8e8f47ae3b598003f76b8564033f001eab03f586ea474aafffa65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFlQvZmvBwpRU3FbrrjmC1MxQNBjMW0fY9TQful1L6MwKjSIvst/ygbrZm/Dqsb3qWewX//CAl/I/sUjAEBrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T09:19:56.147352Z","bundle_sha256":"b6a86aeaaea638689cd70ece3cce9309822096909b2dab43c72004da0b65c21f"}}