{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6FKI3MVNGBUAVHFC2SQN23HO5W","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":"7cfa4424d1bb74c99a833bc03487d01df5e5f0c4bd82ec2f595598ede235c86c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","title_canon_sha256":"6aa295f797c75336a3d0980416668363292f54630f3ae7143d76b900b7b98ee5"},"schema_version":"1.0","source":{"id":"2508.15096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15096","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15096v1","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15096","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_12","alias_value":"6FKI3MVNGBUA","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_16","alias_value":"6FKI3MVNGBUAVHFC","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_8","alias_value":"6FKI3MVN","created_at":"2026-07-05T11:57:06Z"}],"graph_snapshots":[{"event_id":"sha256:7f9903794c22cde039075bafa4ad48c751e037ac08b6172be4a6c83b7c83b57e","target":"graph","created_at":"2026-07-05T11:57:06Z","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/2508.15096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining large language models (LLMs) on high-quality, structured data such as mathematics and code substantially enhances reasoning capabilities. However, existing math-focused datasets built from Common Crawl suffer from degraded quality due to brittle extraction heuristics, lossy HTML-to-text conversion, and the failure to reliably preserve mathematical structure. In this work, we introduce Nemotron-CC-Math, a large-scale, high-quality mathematical corpus constructed from Common Crawl using a novel, domain-agnostic pipeline specifically designed for robust scientific text extraction.\n  U","authors_text":"Bryan Catanzaro, Mohammad Shoeybi, Mostofa Patwary, Rabeeh Karimi Mahabadi, Sanjeev Satheesh, Shrimai Prabhumoye","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15096","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":"sha256:2343d461d3bc1049e7704a3f026f1f771e1921e0c7f6f3edc27576327fc9c1af","target":"record","created_at":"2026-07-05T11:57:06Z","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":"7cfa4424d1bb74c99a833bc03487d01df5e5f0c4bd82ec2f595598ede235c86c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","title_canon_sha256":"6aa295f797c75336a3d0980416668363292f54630f3ae7143d76b900b7b98ee5"},"schema_version":"1.0","source":{"id":"2508.15096","kind":"arxiv","version":1}},"canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","first_computed_at":"2026-07-05T11:57:06.405622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:06.405622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8RzMmZwZcdWx9xb+2dTpREmIOiRJOCS3k768FIAW7GBY1TXtgXZBwASpvuqLDNcT0Y/jnF3kon+Oi2VpCaS4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:06.406120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2343d461d3bc1049e7704a3f026f1f771e1921e0c7f6f3edc27576327fc9c1af","sha256:7f9903794c22cde039075bafa4ad48c751e037ac08b6172be4a6c83b7c83b57e"],"state_sha256":"7a929b517f1fb2d46f0b333b06b0a5d934444661b90c8521c654ebcf9325f9a2"}