{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZKTL75HA3COLTOGNH67FLZQT2S","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":"ab1e42cfc62b8b9841448a5dae91ade59b4321e9500253c4427b6e5e278fd2f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T17:28:50Z","title_canon_sha256":"b93c4078a3f212e72c7381754cfade4304316cfa4050e61836babb3641c82c6f"},"schema_version":"1.0","source":{"id":"2412.02595","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02595","created_at":"2026-07-05T11:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02595v2","created_at":"2026-07-05T11:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02595","created_at":"2026-07-05T11:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZKTL75HA3COL","created_at":"2026-07-05T11:13:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZKTL75HA3COLTOGN","created_at":"2026-07-05T11:13:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZKTL75HA","created_at":"2026-07-05T11:13:16Z"}],"graph_snapshots":[{"event_id":"sha256:085a6997e4b6d18a3dc47c5d58a5086fe31ace50f584e3508fa6fee50d71ee63","target":"graph","created_at":"2026-07-05T11:13:16Z","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/2412.02595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent English Common Crawl datasets like FineWeb-Edu and DCLM achieved significant benchmark gains via aggressive model-based filtering, but at the cost of removing 90% of data. This limits their suitability for long token horizon training, such as 15T tokens for Llama 3.1. In this paper, we show how to achieve better trade-offs between accuracy and data quantity by a combination of classifier ensembling, synthetic data rephrasing, and reduced reliance on heuristic filters. When training 8B parameter models for 1T tokens, using a high-quality subset of our data improves MMLU by 5.6 over DCLM,","authors_text":"Brandon Norick, Bryan Catanzaro, Dan Su, Joseph Jennings, Kezhi Kong, Markus Kliegl, Mohammad Shoeybi, Mostofa Patwary, Ying Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T17:28:50Z","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02595","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":"sha256:4541bdc6b6c6d0562c744b48eef9c00c30370159fefb277756a09e0083936da2","target":"record","created_at":"2026-07-05T11:13:16Z","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":"ab1e42cfc62b8b9841448a5dae91ade59b4321e9500253c4427b6e5e278fd2f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T17:28:50Z","title_canon_sha256":"b93c4078a3f212e72c7381754cfade4304316cfa4050e61836babb3641c82c6f"},"schema_version":"1.0","source":{"id":"2412.02595","kind":"arxiv","version":2}},"canonical_sha256":"caa6bff4e0d89cb9b8cd3fbe55e613d49823b4d7b3984813be47910754652248","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caa6bff4e0d89cb9b8cd3fbe55e613d49823b4d7b3984813be47910754652248","first_computed_at":"2026-07-05T11:13:16.346764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:16.346764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XHZHolmO9ijZPVBrmV9VuknmNyzHUGDM0UGAcwL1Ntzc+Mswu35/zcrT8o6j48c6J1WoASbvrtdFDovJURSjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:16.347287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02595","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4541bdc6b6c6d0562c744b48eef9c00c30370159fefb277756a09e0083936da2","sha256:085a6997e4b6d18a3dc47c5d58a5086fe31ace50f584e3508fa6fee50d71ee63"],"state_sha256":"18474fcfc285447b7b83835267cc45993cf5309ebbe2eef45f38729ecbe9e21c"}