{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DM2DWEW7KQF25NO3MRRJMEEE7K","short_pith_number":"pith:DM2DWEW7","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"},"canonical_sha256":"1b343b12df540baeb5db6462961084fa99872a5917ea16d90194a120451681b3","source":{"kind":"arxiv","id":"2406.01981","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DM2DWEW7KQF25NO3MRRJMEEE7K","target":"record","payload":{"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"},"canonical_sha256":"1b343b12df540baeb5db6462961084fa99872a5917ea16d90194a120451681b3","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"},"source_kind":"arxiv","source_id":"2406.01981","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vy4pUzGKM+tPMER7dW5EDw6T9QfU/6YY50dzcNhg/gIatZg8xXnIYHWoCUpT8JQj63UJ/EmY0NXE54KqHjgKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:22:00.622036Z"},"content_sha256":"ed71993be6e199ad8acd2c4b79791ce3e4b0062a17a93bd9c8e52141e13fa9a0","schema_version":"1.0","event_id":"sha256:ed71993be6e199ad8acd2c4b79791ce3e4b0062a17a93bd9c8e52141e13fa9a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DM2DWEW7KQF25NO3MRRJMEEE7K","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VosDRD7+XbgZsX0uX6HlcfFexz6rNx170GWAKBW0k9bx0TANf7d2vSr5MkElqscRT9+G5vnFGjaMHEGOfrG9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:22:00.622540Z"},"content_sha256":"206c8d3723c6a1ce72f0d055dc394bec741ccb766498902d18f371d8e9918e5d","schema_version":"1.0","event_id":"sha256:206c8d3723c6a1ce72f0d055dc394bec741ccb766498902d18f371d8e9918e5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/bundle.json","state_url":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T20:22:00Z","links":{"resolver":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K","bundle":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/bundle.json","state":"https://pith.science/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DM2DWEW7KQF25NO3MRRJMEEE7K/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ig4pZvmLALqQ7jRVutRA3JQ9n44Kybvbg6E088Fe9FvblgNNgZWDF5xgaUzw9eTqi5SgH4Hy0ybs77IT7jyMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:22:00.626245Z","bundle_sha256":"f3e7f124a963f964f37a4176f992392bbadf41317d82ef85cab52453fc174db0"}}