{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JCLUTLQWPVHJB6SL7PZTPRAQ7Q","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":"8dcff0c2750c4df1ff8e68b918db9700adea64b7ca6ece0789d004be113f4862","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T13:15:15Z","title_canon_sha256":"f4c6c85256023cdecf1912810654e9c036d88949f08e59736d81a25fa37b37e2"},"schema_version":"1.0","source":{"id":"2510.00866","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00866","created_at":"2026-06-24T00:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00866v3","created_at":"2026-06-24T00:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00866","created_at":"2026-06-24T00:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"JCLUTLQWPVHJ","created_at":"2026-06-24T00:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"JCLUTLQWPVHJB6SL","created_at":"2026-06-24T00:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"JCLUTLQW","created_at":"2026-06-24T00:14:21Z"}],"graph_snapshots":[{"event_id":"sha256:269ab2072f25431ed9cdc893137a6dc68b40e478a093baebab035ebfeba3d106","target":"graph","created_at":"2026-06-24T00:14:21Z","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/2510.00866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binary classifier to distinguish between pretraining data and a small, high-quality set. It assigns each pretraining document a quality score defined as the classifier's score and retains only the top-scoring ones. We provide an in-depth analysis of CQF. We show that while CQF improves downstream task performance, it does not necessarily enhance language modeling on the high-quality","authors_text":"David Grangier, Louis Bethune, Marco Cuturi, Michal Klein, Pierre Ablin, Thiziri Nait Saada","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T13:15:15Z","title":"Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00866","kind":"arxiv","version":3},"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":"sha256:9a2fa6ce47344633ac4177eb3e5823d8897ff1b15789a609385e2dc576655779","target":"record","created_at":"2026-06-24T00:14:21Z","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":"8dcff0c2750c4df1ff8e68b918db9700adea64b7ca6ece0789d004be113f4862","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T13:15:15Z","title_canon_sha256":"f4c6c85256023cdecf1912810654e9c036d88949f08e59736d81a25fa37b37e2"},"schema_version":"1.0","source":{"id":"2510.00866","kind":"arxiv","version":3}},"canonical_sha256":"489749ae167d4e90fa4bfbf337c410fc357e300b7234efa95b3113d7646a380b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"489749ae167d4e90fa4bfbf337c410fc357e300b7234efa95b3113d7646a380b","first_computed_at":"2026-06-24T00:14:21.161280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:21.161280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dN3OCdmZY/MAIPceQfQs/CMC/2XWztKCCJ5sd4jgUd1na5AgBILEUhG5CSjsrPOjLp8rMCvfELLir9kjFgazBw==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:21.161735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.00866","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a2fa6ce47344633ac4177eb3e5823d8897ff1b15789a609385e2dc576655779","sha256:269ab2072f25431ed9cdc893137a6dc68b40e478a093baebab035ebfeba3d106"],"state_sha256":"f634f69d9e32028d834a62d695e0d3357fef05faab80111a5fa32f8ac449def3"}