{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6IXVWWO4WRT5VT36XR6GW7BB26","short_pith_number":"pith:6IXVWWO4","canonical_record":{"source":{"id":"2403.09629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T17:58:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58f96fea8ecf1be0ee9111de3692519516364c20b44332de0796546b9a2d27b3","abstract_canon_sha256":"f4409e4df469e5e7ae3e3127a2895fc4e2c1d886a715f729ec104cf299962786"},"schema_version":"1.0"},"canonical_sha256":"f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22","source":{"kind":"arxiv","id":"2403.09629","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09629","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09629v2","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09629","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"6IXVWWO4WRT5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6IXVWWO4WRT5VT36","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6IXVWWO4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6IXVWWO4WRT5VT36XR6GW7BB26","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T17:58:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58f96fea8ecf1be0ee9111de3692519516364c20b44332de0796546b9a2d27b3","abstract_canon_sha256":"f4409e4df469e5e7ae3e3127a2895fc4e2c1d886a715f729ec104cf299962786"},"schema_version":"1.0"},"canonical_sha256":"f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.939552Z","signature_b64":"7uSeFEMQuOcfHECs22iO/spCHPuuFs2CYumyDljFfg4O5wlAxRR+KjPDjTq9qrwt2/xOwkcD5xn0WBGXD/dGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22","last_reissued_at":"2026-05-17T23:38:48.938887Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.938887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09629","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HA5GI33n2jsbhHRGf/UKqSUCaeM7y6kuVkVHUAOKkidJSy9ilr0AOY+xIutMrXRjeyHlm7n87Kn8uZqf0SLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:25:43.971944Z"},"content_sha256":"f06dcbd6339bd7966de73a4808f53f0ce73a408fe6eeef715d9c34484595b1d1","schema_version":"1.0","event_id":"sha256:f06dcbd6339bd7966de73a4808f53f0ce73a408fe6eeef715d9c34484595b1d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6IXVWWO4WRT5VT36XR6GW7BB26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Language models learn to generate rationales before each token during pretraining to improve future predictions.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric Zelikman, Georges Harik, Nick Haber, Noah D. Goodman, Varuna Jayasiri, Yijia Shao","submitted_at":"2024-03-14T17:58:16Z","abstract_excerpt":"When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For example, this applies to the steps not stated between the lines of a proof or to the theory of mind underlying a conversation. In the Self-Taught Reasoner (STaR, Zelikman et al. 2022), useful thinking is learned by inferring rationales from few-shot examples in question-answering and learning from those that lead to a correct answer. This is a highly constrain"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"after continued pretraining of an LM on a corpus of internet text with Quiet-STaR, we find zero-shot improvements on GSM8K (5.9%→10.9%) and CommonsenseQA (36.3%→47.2%) and observe a perplexity improvement of difficult tokens in natural text. Crucially, these improvements require no fine-tuning on these tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that language models can initially learn to generate and effectively use internal rationales at each token to improve future text predictions, despite starting without knowledge of how to produce or apply such thoughts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Quiet-STaR lets language models learn token-level rationales from general text, producing zero-shot gains on GSM8K and CommonsenseQA after continued pretraining.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Language models learn to generate rationales before each token during pretraining to improve future predictions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"47c35d1a2b12b3a20a2052f6e5cbd47487ea4f547908a6128edffc170b693f84"},"source":{"id":"2403.09629","kind":"arxiv","version":2},"verdict":{"id":"2efc4cb0-63fa-480d-bfc3-98a93b734c39","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T05:40:09.548591Z","strongest_claim":"after continued pretraining of an LM on a corpus of internet text with Quiet-STaR, we find zero-shot improvements on GSM8K (5.9%→10.9%) and CommonsenseQA (36.3%→47.2%) and observe a perplexity improvement of difficult tokens in natural text. Crucially, these improvements require no fine-tuning on these tasks.","one_line_summary":"Quiet-STaR lets language models learn token-level rationales from general text, producing zero-shot gains on GSM8K and CommonsenseQA after continued pretraining.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that language models can initially learn to generate and effectively use internal rationales at each token to improve future text predictions, despite starting without knowledge of how to produce or apply such thoughts.","pith_extraction_headline":"Language models learn to generate rationales before each token during pretraining to improve future predictions."},"references":{"count":8,"sample":[{"doi":"","year":2022,"title":"Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, and Noah D Goodman","work_id":"bfe85e1d-9d73-4e75-b743-317ebeac74e4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Janet sells an average of 12 fresh duck eggs daily on the farmers ' market. If she sells them for $2 per egg how much does she make per week, assuming she sells at the farmers ' market most every day?","work_id":"78289726-4d72-4a00-b34e-9e6a2707e52b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The ducks lay 16 eggs per day","work_id":"87c6b6ff-7724-44a4-8bb8-4b2814bd955e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"She eats 3 for breakfast every morning","work_id":"44486531-8b96-42db-8906-bd3ea8eb8cbd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"She bakes muffins for her friends every day with 4","work_id":"f07ac092-ec3c-46b1-bd3b-c78de04d9268","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":8,"snapshot_sha256":"62dc2eee18ce92f5d42bd7d9a9d9724af1338708a9b023bb2feaa71ff57dd301","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":"2efc4cb0-63fa-480d-bfc3-98a93b734c39"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MAWNTA1hZdeGAL2gSAUlIQii55msdExsz2iVeTKWu++VIzgjqayb0Mn6ACGCpby3DYFhg4DwFJyOA92j/09BAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:25:43.972973Z"},"content_sha256":"349c60db6260d7aeae2eede2c5f00b7ac64a97090bb4cf807c3fe7becdf876cb","schema_version":"1.0","event_id":"sha256:349c60db6260d7aeae2eede2c5f00b7ac64a97090bb4cf807c3fe7becdf876cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6IXVWWO4WRT5VT36XR6GW7BB26/bundle.json","state_url":"https://pith.science/pith/6IXVWWO4WRT5VT36XR6GW7BB26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6IXVWWO4WRT5VT36XR6GW7BB26/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":"2026-05-30T06:25:43Z","links":{"resolver":"https://pith.science/pith/6IXVWWO4WRT5VT36XR6GW7BB26","bundle":"https://pith.science/pith/6IXVWWO4WRT5VT36XR6GW7BB26/bundle.json","state":"https://pith.science/pith/6IXVWWO4WRT5VT36XR6GW7BB26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6IXVWWO4WRT5VT36XR6GW7BB26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6IXVWWO4WRT5VT36XR6GW7BB26","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":"f4409e4df469e5e7ae3e3127a2895fc4e2c1d886a715f729ec104cf299962786","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T17:58:16Z","title_canon_sha256":"58f96fea8ecf1be0ee9111de3692519516364c20b44332de0796546b9a2d27b3"},"schema_version":"1.0","source":{"id":"2403.09629","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09629","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09629v2","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09629","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"6IXVWWO4WRT5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6IXVWWO4WRT5VT36","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6IXVWWO4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:349c60db6260d7aeae2eede2c5f00b7ac64a97090bb4cf807c3fe7becdf876cb","target":"graph","created_at":"2026-05-17T23:38:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"after continued pretraining of an LM on a corpus of internet text with Quiet-STaR, we find zero-shot improvements on GSM8K (5.9%→10.9%) and CommonsenseQA (36.3%→47.2%) and observe a perplexity improvement of difficult tokens in natural text. Crucially, these improvements require no fine-tuning on these tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"that language models can initially learn to generate and effectively use internal rationales at each token to improve future text predictions, despite starting without knowledge of how to produce or apply such thoughts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Quiet-STaR lets language models learn token-level rationales from general text, producing zero-shot gains on GSM8K and CommonsenseQA after continued pretraining."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Language models learn to generate rationales before each token during pretraining to improve future predictions."}],"snapshot_sha256":"47c35d1a2b12b3a20a2052f6e5cbd47487ea4f547908a6128edffc170b693f84"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For example, this applies to the steps not stated between the lines of a proof or to the theory of mind underlying a conversation. In the Self-Taught Reasoner (STaR, Zelikman et al. 2022), useful thinking is learned by inferring rationales from few-shot examples in question-answering and learning from those that lead to a correct answer. This is a highly constrain","authors_text":"Eric Zelikman, Georges Harik, Nick Haber, Noah D. Goodman, Varuna Jayasiri, Yijia Shao","cross_cats":["cs.AI","cs.LG"],"headline":"Language models learn to generate rationales before each token during pretraining to improve future predictions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T17:58:16Z","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking"},"references":{"count":8,"internal_anchors":0,"resolved_work":8,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, and Noah D Goodman","work_id":"bfe85e1d-9d73-4e75-b743-317ebeac74e4","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Janet sells an average of 12 fresh duck eggs daily on the farmers ' market. If she sells them for $2 per egg how much does she make per week, assuming she sells at the farmers ' market most every day?","work_id":"78289726-4d72-4a00-b34e-9e6a2707e52b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The ducks lay 16 eggs per day","work_id":"87c6b6ff-7724-44a4-8bb8-4b2814bd955e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"She eats 3 for breakfast every morning","work_id":"44486531-8b96-42db-8906-bd3ea8eb8cbd","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"She bakes muffins for her friends every day with 4","work_id":"f07ac092-ec3c-46b1-bd3b-c78de04d9268","year":null}],"snapshot_sha256":"62dc2eee18ce92f5d42bd7d9a9d9724af1338708a9b023bb2feaa71ff57dd301"},"source":{"id":"2403.09629","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T05:40:09.548591Z","id":"2efc4cb0-63fa-480d-bfc3-98a93b734c39","model_set":{"reader":"grok-4.3"},"one_line_summary":"Quiet-STaR lets language models learn token-level rationales from general text, producing zero-shot gains on GSM8K and CommonsenseQA after continued pretraining.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Language models learn to generate rationales before each token during pretraining to improve future predictions.","strongest_claim":"after continued pretraining of an LM on a corpus of internet text with Quiet-STaR, we find zero-shot improvements on GSM8K (5.9%→10.9%) and CommonsenseQA (36.3%→47.2%) and observe a perplexity improvement of difficult tokens in natural text. Crucially, these improvements require no fine-tuning on these tasks.","weakest_assumption":"that language models can initially learn to generate and effectively use internal rationales at each token to improve future text predictions, despite starting without knowledge of how to produce or apply such thoughts."}},"verdict_id":"2efc4cb0-63fa-480d-bfc3-98a93b734c39"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f06dcbd6339bd7966de73a4808f53f0ce73a408fe6eeef715d9c34484595b1d1","target":"record","created_at":"2026-05-17T23:38:48Z","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":"f4409e4df469e5e7ae3e3127a2895fc4e2c1d886a715f729ec104cf299962786","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T17:58:16Z","title_canon_sha256":"58f96fea8ecf1be0ee9111de3692519516364c20b44332de0796546b9a2d27b3"},"schema_version":"1.0","source":{"id":"2403.09629","kind":"arxiv","version":2}},"canonical_sha256":"f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22","first_computed_at":"2026-05-17T23:38:48.938887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.938887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7uSeFEMQuOcfHECs22iO/spCHPuuFs2CYumyDljFfg4O5wlAxRR+KjPDjTq9qrwt2/xOwkcD5xn0WBGXD/dGCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.939552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09629","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f06dcbd6339bd7966de73a4808f53f0ce73a408fe6eeef715d9c34484595b1d1","sha256:349c60db6260d7aeae2eede2c5f00b7ac64a97090bb4cf807c3fe7becdf876cb"],"state_sha256":"c795bd3696a763809fb1a3c209ced7a8e058a23cea7edf88b62fc8a2ace0a6ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/eSI2iSAxQOIf5rW0PekQPEkt3hQlvIxkFgZmtBmnw12TuA3fh3dQnZAgb8GEsBdqMe0g0urHPedD0gH6UoMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T06:25:43.977231Z","bundle_sha256":"de912271c7aaba421150a895bbfce5433329b4ffd4934f21fdf3edd766b73c6e"}}