{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6NIHJWXXHOHV7DWN36PTOH4K5O","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":"1c65e8667a682357a3a60abec86dfb5db98bc6bde695dbcac93e16ec38f80a5c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T04:57:41Z","title_canon_sha256":"f5a5fc3f0a627db59cf02c728564d1665d6aaa1bab127ca53297e333575d5da9"},"schema_version":"1.0","source":{"id":"2411.06068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06068","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06068v1","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06068","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"6NIHJWXXHOHV","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"6NIHJWXXHOHV7DWN","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"6NIHJWXX","created_at":"2026-07-05T09:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:1fa15783b2b2b6f28fd2e991b589acf4d4fb28a61f6994e20e0da5ac44626831","target":"graph","created_at":"2026-07-05T09:33:16Z","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/2411.06068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this technical report, we present Zyda-2: a five trillion token dataset for language model pretraining. Zyda-2 was used to train our Zamba2 series of models which are state-of-the-art for their weight class. We build Zyda-2 by collating high-quality open-source tokens such as FineWeb and DCLM, then distilling them to the highest-quality subset via cross-deduplication and model-based quality filtering. Zyda-2 is released under a permissive open license, and is available at https://huggingface.co/datasets/Zyphra/Zyda-2","authors_text":"Beren Millidge, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T04:57:41Z","title":"Zyda-2: a 5 Trillion Token High-Quality Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06068","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:d725a872b4ce21877d154669d7afc0baba4ba06165701f8f3357c1d6c07514e4","target":"record","created_at":"2026-07-05T09:33:16Z","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":"1c65e8667a682357a3a60abec86dfb5db98bc6bde695dbcac93e16ec38f80a5c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T04:57:41Z","title_canon_sha256":"f5a5fc3f0a627db59cf02c728564d1665d6aaa1bab127ca53297e333575d5da9"},"schema_version":"1.0","source":{"id":"2411.06068","kind":"arxiv","version":1}},"canonical_sha256":"f35074daf73b8f5f8ecddf9f371f8aeba576c01eec87cb16abc149b6637446c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f35074daf73b8f5f8ecddf9f371f8aeba576c01eec87cb16abc149b6637446c6","first_computed_at":"2026-07-05T09:33:16.518164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:16.518164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3elKUQDdluNUW1QnDXnRPWntMVW3Gpq3eh35Kp1GVcvGv/qUpgK33r99AEY0Q3ITqWt5Fw5mJyWQFPVxA+IxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:16.518853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d725a872b4ce21877d154669d7afc0baba4ba06165701f8f3357c1d6c07514e4","sha256:1fa15783b2b2b6f28fd2e991b589acf4d4fb28a61f6994e20e0da5ac44626831"],"state_sha256":"d7efa7358d263cb3a2647342a80c8d2c0ed16f67119a72d771bd39f86f8bc765"}