{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:45QXWJA7VQ35I4EVJQDVEGH6GD","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":"68daf6501de579b9c4cadf455128b37d333cb03a6977a184a5d4a97b5ed527f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T20:29:50Z","title_canon_sha256":"09b50f107032512f405f2d04ef485efc3060e32f7623d7ded9826468d20103e4"},"schema_version":"1.0","source":{"id":"2402.00159","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00159","created_at":"2026-07-05T08:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00159v2","created_at":"2026-07-05T08:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00159","created_at":"2026-07-05T08:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"45QXWJA7VQ35","created_at":"2026-07-05T08:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"45QXWJA7VQ35I4EV","created_at":"2026-07-05T08:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"45QXWJA7","created_at":"2026-07-05T08:28:37Z"}],"graph_snapshots":[{"event_id":"sha256:417c782f8052c7ac59f92cbbd1a518bedbbbca1f896d96b4bcac064e3ff58d12","target":"graph","created_at":"2026-07-05T08:28:37Z","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/2402.00159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information about pretraining corpora used to train the current best-performing language models is seldom discussed: commercial models rarely detail their data, and even open models are often released without accompanying training data or recipes to reproduce them. As a result, it is challenging to conduct and advance scientific research on language modeling, such as understanding how training data impacts model capabilities and limitations. To facilitate scientific research on language model pretraining, we curate and release Dolma, a three-trillion-token English corpus, built from a diverse ","authors_text":"Aakanksha Naik, Abhilasha Ravichander, Akshita Bhagia, Ananya Harsh Jha, Ben Bogin, Crystal Nam, David Atkinson, Dirk Groeneveld, Dustin Schwenk, Emma Strubell, Hannaneh Hajishirzi, Ian Magnusson, Iz Beltagy, Jacob Morrison, Jennifer Dumas, Jesse Dodge, Khyathi Chandu, Kyle Lo, Kyle Richardson, Li Lucy, Luca Soldaini, Luke Zettlemoyer, Matthew E. Peters, Nathan Lambert, Niklas Muennighoff, Nishant Subramani, Noah A. Smith, Oyvind Tafjord, Pete Walsh, Rodney Kinney, Russell Authur, Sachin Kumar, Valentin Hofmann, Xinxi Lyu, Yanai Elazar, Zejiang Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T20:29:50Z","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00159","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":"sha256:97c6e8bfdd326681f64994437c8a4c289ebbf5702151b3527f7a0ac9bfd6b63a","target":"record","created_at":"2026-07-05T08:28:37Z","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":"68daf6501de579b9c4cadf455128b37d333cb03a6977a184a5d4a97b5ed527f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T20:29:50Z","title_canon_sha256":"09b50f107032512f405f2d04ef485efc3060e32f7623d7ded9826468d20103e4"},"schema_version":"1.0","source":{"id":"2402.00159","kind":"arxiv","version":2}},"canonical_sha256":"e7617b241fac37d470954c075218fe30db82c2cf5f8e8a8af316ba8aee6668c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7617b241fac37d470954c075218fe30db82c2cf5f8e8a8af316ba8aee6668c9","first_computed_at":"2026-07-05T08:28:37.468057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:37.468057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y4Pch9OB4jpwjD73xrrnzKjfRn2ONw2rTVQv9EBQMgmkEP2t5aFGm592v8NXBlDPdrxl1Ce9WqsHpJB3uE4FCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:37.468546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00159","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97c6e8bfdd326681f64994437c8a4c289ebbf5702151b3527f7a0ac9bfd6b63a","sha256:417c782f8052c7ac59f92cbbd1a518bedbbbca1f896d96b4bcac064e3ff58d12"],"state_sha256":"fe1af5eb3766de07f882499fc27c0c33b36a769233a5161691515da6d3f18410"}