{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P3CCYFWMQIVEHVRQAAJRBVHH3X","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":"1c8e9f1aabbc577b0f5b3cb24784bd12c2ec47e375ff42d228aaacc2c573be75","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T19:34:05Z","title_canon_sha256":"a1464dd88ef7a77013e5734d39d6164651dd3f1e5060b8c2a6d22987e5a50e12"},"schema_version":"1.0","source":{"id":"2309.04564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04564","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04564v1","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04564","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"P3CCYFWMQIVE","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"P3CCYFWMQIVEHVRQ","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"P3CCYFWM","created_at":"2026-07-05T06:49:04Z"}],"graph_snapshots":[{"event_id":"sha256:613f479c66d0f837036d8a4018fec555a13cb36f7731e03137b6238cbe4825a8","target":"graph","created_at":"2026-07-05T06:49:04Z","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/2309.04564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web text. To date, efforts to prune these datasets down to a higher quality subset have relied on hand-crafted heuristics encoded as rule-based filters. In this work, we take a wider view and explore scalable estimates of data quality that can be used to systematically measure the quality of pretraining data. We perform a rigorous comparison at scale of the simpl","authors_text":"Ahmet \\\"Ust\\\"un, Alex Wang, Luiza Pozzobon, Marzieh Fadaee, Max Marion, Sara Hooker","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T19:34:05Z","title":"When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04564","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":"sha256:44d22e544554bbd7adcc72463b5188dbbf06ecb68fc5a3c000f3694ffe8d915d","target":"record","created_at":"2026-07-05T06:49:04Z","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":"1c8e9f1aabbc577b0f5b3cb24784bd12c2ec47e375ff42d228aaacc2c573be75","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T19:34:05Z","title_canon_sha256":"a1464dd88ef7a77013e5734d39d6164651dd3f1e5060b8c2a6d22987e5a50e12"},"schema_version":"1.0","source":{"id":"2309.04564","kind":"arxiv","version":1}},"canonical_sha256":"7ec42c16cc822a43d630001310d4e7ddf91989b9fdfd90d2164258ccc27bcd80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec42c16cc822a43d630001310d4e7ddf91989b9fdfd90d2164258ccc27bcd80","first_computed_at":"2026-07-05T06:49:04.972662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:04.972662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uo9o9/WHLb63NznUVCCqIsRW2US5/Lh5Mgd1gBk3VrfWNlQOqYCHCG+w6px+MPGOoiqUK25q+BtERpSUjPDFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:04.973129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44d22e544554bbd7adcc72463b5188dbbf06ecb68fc5a3c000f3694ffe8d915d","sha256:613f479c66d0f837036d8a4018fec555a13cb36f7731e03137b6238cbe4825a8"],"state_sha256":"39f49b1b08e572d34303e573ebc43a1410abca371ead70f79f90e26ad5187795"}