{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R5JUZ6AROJRHG3PF6BP7BPOFEK","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":"b64025c1433ad4bfd089a7d3ed46285d6303a2aa54237e73eab5b6d4ccf0b5e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T13:59:56Z","title_canon_sha256":"a8d2575bb56028cf85558d62f314be2d43e56037178d28a8eb213f3ef17cf536"},"schema_version":"1.0","source":{"id":"2402.04004","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04004","created_at":"2026-07-05T07:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04004v2","created_at":"2026-07-05T07:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04004","created_at":"2026-07-05T07:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"R5JUZ6AROJRH","created_at":"2026-07-05T07:43:15Z"},{"alias_kind":"pith_short_16","alias_value":"R5JUZ6AROJRHG3PF","created_at":"2026-07-05T07:43:15Z"},{"alias_kind":"pith_short_8","alias_value":"R5JUZ6AR","created_at":"2026-07-05T07:43:15Z"}],"graph_snapshots":[{"event_id":"sha256:3a3812df2161d3041841d55bc374c78abb3c95532c97cb21e8a317243e1e2c2e","target":"graph","created_at":"2026-07-05T07:43:15Z","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/2402.04004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During both pretraining and fine-tuning, Large Language Models (\\textbf{LLMs}) are trained on trillions of tokens of text of widely varying quality. Both phases of training typically involve heuristically filtering out ``low-quality'' or \\textit{noisy} training samples, yet little is known quantitatively about how the type or intensity of noise affects downstream performance. In this work, we study how noise in chain of thought (\\textbf{CoT}) impacts task performance in the highly-controlled setting of algorithmically solvable tasks. First, we develop the Traced Integer (\\textbf{TInt}) framewo","authors_text":"Alex Havrilla, Maia Iyer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T13:59:56Z","title":"Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04004","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:d3421e863b1c5b51b0f695d31c46849edcae11bf09c56b1f64e83352d246ce8f","target":"record","created_at":"2026-07-05T07:43:15Z","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":"b64025c1433ad4bfd089a7d3ed46285d6303a2aa54237e73eab5b6d4ccf0b5e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T13:59:56Z","title_canon_sha256":"a8d2575bb56028cf85558d62f314be2d43e56037178d28a8eb213f3ef17cf536"},"schema_version":"1.0","source":{"id":"2402.04004","kind":"arxiv","version":2}},"canonical_sha256":"8f534cf8117262736de5f05ff0bdc522858f9c3dc86f35b228eabb2cb6dea1d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f534cf8117262736de5f05ff0bdc522858f9c3dc86f35b228eabb2cb6dea1d3","first_computed_at":"2026-07-05T07:43:15.112748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:15.112748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCCnlhov5uqVbBBhkMrV8LHWNBJCFPHOb9GIYZKPjIJisWbOSVE8LVDHQmUYIqQGtE8Pjs7RmD/XOyo0HS0rDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:15.113261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04004","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3421e863b1c5b51b0f695d31c46849edcae11bf09c56b1f64e83352d246ce8f","sha256:3a3812df2161d3041841d55bc374c78abb3c95532c97cb21e8a317243e1e2c2e"],"state_sha256":"3917f28be1a84e4bc0e87c6a1a45c54186841ee417fa12a7280fc60935dafb4a"}