{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6NIHJWXXHOHV7DWN36PTOH4K5O","short_pith_number":"pith:6NIHJWXX","canonical_record":{"source":{"id":"2411.06068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T04:57:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5a5fc3f0a627db59cf02c728564d1665d6aaa1bab127ca53297e333575d5da9","abstract_canon_sha256":"1c65e8667a682357a3a60abec86dfb5db98bc6bde695dbcac93e16ec38f80a5c"},"schema_version":"1.0"},"canonical_sha256":"f35074daf73b8f5f8ecddf9f371f8aeba576c01eec87cb16abc149b6637446c6","source":{"kind":"arxiv","id":"2411.06068","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6NIHJWXXHOHV7DWN36PTOH4K5O","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T04:57:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5a5fc3f0a627db59cf02c728564d1665d6aaa1bab127ca53297e333575d5da9","abstract_canon_sha256":"1c65e8667a682357a3a60abec86dfb5db98bc6bde695dbcac93e16ec38f80a5c"},"schema_version":"1.0"},"canonical_sha256":"f35074daf73b8f5f8ecddf9f371f8aeba576c01eec87cb16abc149b6637446c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:16.518853Z","signature_b64":"3elKUQDdluNUW1QnDXnRPWntMVW3Gpq3eh35Kp1GVcvGv/qUpgK33r99AEY0Q3ITqWt5Fw5mJyWQFPVxA+IxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35074daf73b8f5f8ecddf9f371f8aeba576c01eec87cb16abc149b6637446c6","last_reissued_at":"2026-07-05T09:33:16.518164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:16.518164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06068","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wIcrbOdt9zrTmN7EEsAKuTLOBot50W6psN/mds8xMj8xZybAHY1ilkuoMI7eJu6X2X/WGvu6YxBuNnnM9NdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:58:11.948372Z"},"content_sha256":"d725a872b4ce21877d154669d7afc0baba4ba06165701f8f3357c1d6c07514e4","schema_version":"1.0","event_id":"sha256:d725a872b4ce21877d154669d7afc0baba4ba06165701f8f3357c1d6c07514e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6NIHJWXXHOHV7DWN36PTOH4K5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zyda-2: a 5 Trillion Token High-Quality Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beren Millidge, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","submitted_at":"2024-11-09T04:57:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06068","kind":"arxiv","version":1},"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/2411.06068/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":"2026-07-05T09:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCDtBMOQBV2tdRgLwzbm9RZ38GdgH7DKl/06Yu20cnU78xj4CWP8i5rCfsL0eL8WGAzgiA+P6WNPLXuF0pQoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:58:11.949390Z"},"content_sha256":"1fa15783b2b2b6f28fd2e991b589acf4d4fb28a61f6994e20e0da5ac44626831","schema_version":"1.0","event_id":"sha256:1fa15783b2b2b6f28fd2e991b589acf4d4fb28a61f6994e20e0da5ac44626831"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NIHJWXXHOHV7DWN36PTOH4K5O/bundle.json","state_url":"https://pith.science/pith/6NIHJWXXHOHV7DWN36PTOH4K5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NIHJWXXHOHV7DWN36PTOH4K5O/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":"2026-08-14T19:58:11Z","links":{"resolver":"https://pith.science/pith/6NIHJWXXHOHV7DWN36PTOH4K5O","bundle":"https://pith.science/pith/6NIHJWXXHOHV7DWN36PTOH4K5O/bundle.json","state":"https://pith.science/pith/6NIHJWXXHOHV7DWN36PTOH4K5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NIHJWXXHOHV7DWN36PTOH4K5O/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpusAJQDUXNLNicNMhcD8Onvga3OnOQoydg8TPLuoA0tgwTZ4y4Iil1BdUJweVlUpRanveG9hfvCuKsXLlJEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:58:11.956583Z","bundle_sha256":"a098334ebf77c220b9b8e2cb282cc340bf15a2b357a093376e460f7619de3fe2"}}