{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DM2DWEW7KQF25NO3MRRJMEEE7K","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":"6f64ffcbafc6aec72ab07fcf172e75de79c26d586d99a18343302201bc01a877","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T05:47:17Z","title_canon_sha256":"6c1d286dac9d31c11ec22a00bcbf4435a937b8783cca54ab8c86eff889a24ae7"},"schema_version":"1.0","source":{"id":"2406.01981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01981","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01981v2","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01981","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"DM2DWEW7KQF2","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"DM2DWEW7KQF25NO3","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"DM2DWEW7","created_at":"2026-07-05T09:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:206c8d3723c6a1ce72f0d055dc394bec741ccb766498902d18f371d8e9918e5d","target":"graph","created_at":"2026-07-05T09:02:41Z","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/2406.01981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The size of large language models (LLMs) has scaled dramatically in recent years and their computational and data requirements have surged correspondingly. State-of-the-art language models, even at relatively smaller sizes, typically require training on at least a trillion tokens. This rapid advancement has eclipsed the growth of open-source datasets available for large-scale LLM pretraining. In this paper, we introduce Zyda (Zyphra Dataset), a dataset under a permissive license comprising 1.3 trillion tokens, assembled by integrating several major respected open-source datasets into a single,","authors_text":"Adam Ibrahim, Beren Millidge, James Whittington, Jonathan Pilault, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T05:47:17Z","title":"Zyda: A 1.3T Dataset for Open Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01981","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:ed71993be6e199ad8acd2c4b79791ce3e4b0062a17a93bd9c8e52141e13fa9a0","target":"record","created_at":"2026-07-05T09:02:41Z","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":"6f64ffcbafc6aec72ab07fcf172e75de79c26d586d99a18343302201bc01a877","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T05:47:17Z","title_canon_sha256":"6c1d286dac9d31c11ec22a00bcbf4435a937b8783cca54ab8c86eff889a24ae7"},"schema_version":"1.0","source":{"id":"2406.01981","kind":"arxiv","version":2}},"canonical_sha256":"1b343b12df540baeb5db6462961084fa99872a5917ea16d90194a120451681b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b343b12df540baeb5db6462961084fa99872a5917ea16d90194a120451681b3","first_computed_at":"2026-07-05T09:02:41.211341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:41.211341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7sPNcZb5uXP9MK1kL6jIX7gOsCD1XZRrRinEPOtH+HkEJWfARO3F1LU3tZadQ8H3mlrSCn66HK1T6BFVomYHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:41.211824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed71993be6e199ad8acd2c4b79791ce3e4b0062a17a93bd9c8e52141e13fa9a0","sha256:206c8d3723c6a1ce72f0d055dc394bec741ccb766498902d18f371d8e9918e5d"],"state_sha256":"0bb2a42a3943baa0287d441591171523609e9aa5267d5dc080b39115feb8f388"}