{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DM2DWEW7KQF25NO3MRRJMEEE7K","short_pith_number":"pith:DM2DWEW7","schema_version":"1.0","canonical_sha256":"1b343b12df540baeb5db6462961084fa99872a5917ea16d90194a120451681b3","source":{"kind":"arxiv","id":"2406.01981","version":2},"attestation_state":"computed","paper":{"title":"Zyda: A 1.3T Dataset for Open Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Ibrahim, Beren Millidge, James Whittington, Jonathan Pilault, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","submitted_at":"2024-06-04T05:47:17Z","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.01981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T05:47:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c1d286dac9d31c11ec22a00bcbf4435a937b8783cca54ab8c86eff889a24ae7","abstract_canon_sha256":"6f64ffcbafc6aec72ab07fcf172e75de79c26d586d99a18343302201bc01a877"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:41.211824Z","signature_b64":"7sPNcZb5uXP9MK1kL6jIX7gOsCD1XZRrRinEPOtH+HkEJWfARO3F1LU3tZadQ8H3mlrSCn66HK1T6BFVomYHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b343b12df540baeb5db6462961084fa99872a5917ea16d90194a120451681b3","last_reissued_at":"2026-07-05T09:02:41.211341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:41.211341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zyda: A 1.3T Dataset for Open Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Ibrahim, Beren Millidge, James Whittington, Jonathan Pilault, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","submitted_at":"2024-06-04T05:47:17Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01981","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.01981/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.01981","created_at":"2026-07-05T09:02:41.211400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01981v2","created_at":"2026-07-05T09:02:41.211400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01981","created_at":"2026-07-05T09:02:41.211400+00:00"},{"alias_kind":"pith_short_12","alias_value":"DM2DWEW7KQF2","created_at":"2026-07-05T09:02:41.211400+00:00"},{"alias_kind":"pith_short_16","alias_value":"DM2DWEW7KQF25NO3","created_at":"2026-07-05T09:02:41.211400+00:00"},{"alias_kind":"pith_short_8","alias_value":"DM2DWEW7","created_at":"2026-07-05T09:02:41.211400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05365","citing_title":"ZAYA1-8B Technical Report","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K","json":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K.json","graph_json":"https://pith.science/api/pith-number/DM2DWEW7KQF25NO3MRRJMEEE7K/graph.json","events_json":"https://pith.science/api/pith-number/DM2DWEW7KQF25NO3MRRJMEEE7K/events.json","paper":"https://pith.science/paper/DM2DWEW7"},"agent_actions":{"view_html":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K","download_json":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K.json","view_paper":"https://pith.science/paper/DM2DWEW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01981&json=true","fetch_graph":"https://pith.science/api/pith-number/DM2DWEW7KQF25NO3MRRJMEEE7K/graph.json","fetch_events":"https://pith.science/api/pith-number/DM2DWEW7KQF25NO3MRRJMEEE7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/action/storage_attestation","attest_author":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/action/author_attestation","sign_citation":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/action/citation_signature","submit_replication":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/action/replication_record"}},"created_at":"2026-07-05T09:02:41.211400+00:00","updated_at":"2026-07-05T09:02:41.211400+00:00"}