{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZITBFQGGT752GCV6ZTOSYO6ZHR","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":"156b8dcb0c08951654d1ff370cce2e9156a1dba95c9c392448062928022b6834","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-09T02:34:01Z","title_canon_sha256":"b9e6115bbbdd2659dd8b2451296c3ba0a50179e203a55056b845680b29e8865c"},"schema_version":"1.0","source":{"id":"2309.04662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04662","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04662v1","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04662","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZITBFQGGT752","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZITBFQGGT752GCV6","created_at":"2026-07-05T06:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZITBFQGG","created_at":"2026-07-05T06:49:07Z"}],"graph_snapshots":[{"event_id":"sha256:25ef62b4b625c83e9755f3343a7ae7615c779f7aa22f473a0c4f74e0602a4cc6","target":"graph","created_at":"2026-07-05T06:49:07Z","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/2309.04662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages. We discuss the limitations revealed by self-auditing MADLAD-400, and the role data auditing had in the dataset creation process. We then train and release a 10.7B-parameter multilingual machine translation model on 250 billion tokens covering over 450 languages using publicly available data, and find that it is competitive with models that are significantly larger, and report the results on different domains. In addition, we train a 8B-parameter language model,","authors_text":"Aditya Kusupati, Ankur Bapna, Biao Zhang, Christopher A. Choquette-Choo, Derrick Xin, Isaac Caswell, Katherine Lee, Orhan Firat, Romi Stella, Sneha Kudugunta, Xavier Garcia","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-09T02:34:01Z","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04662","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":"sha256:63ced52bab9f9d91731bb7e8cc1c409dabc6322e3908be80a88b213311801dc2","target":"record","created_at":"2026-07-05T06:49:07Z","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":"156b8dcb0c08951654d1ff370cce2e9156a1dba95c9c392448062928022b6834","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-09T02:34:01Z","title_canon_sha256":"b9e6115bbbdd2659dd8b2451296c3ba0a50179e203a55056b845680b29e8865c"},"schema_version":"1.0","source":{"id":"2309.04662","kind":"arxiv","version":1}},"canonical_sha256":"ca2612c0c69ffba30abeccdd2c3bd93c61e4e45ed910b7ecc5840ff9bbac8987","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca2612c0c69ffba30abeccdd2c3bd93c61e4e45ed910b7ecc5840ff9bbac8987","first_computed_at":"2026-07-05T06:49:07.133458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:07.133458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vk5KCCo7RaiHhYNBAb+5CAEQTV1MvBEN4CbrICVS6J+KYabvAJiBFmO10yacJyYmhzi3EKLPmuHfLRH1V2qzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:07.133924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63ced52bab9f9d91731bb7e8cc1c409dabc6322e3908be80a88b213311801dc2","sha256:25ef62b4b625c83e9755f3343a7ae7615c779f7aa22f473a0c4f74e0602a4cc6"],"state_sha256":"28a8885a74f3771eba50c788752f9de47caa1bbfb8f542db64c10fdc6df4f4b1"}