{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YENANHR4AIWZ4TXAWDTE4OUFUL","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":"dcbe79f403641e164a2f430654bc7f0e1f024041db5a71cff266e71081b5882e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:18Z","title_canon_sha256":"5078e01958947bdafeafc2534defbc5622802935ef6fdb1806bb4a73ece2d769"},"schema_version":"1.0","source":{"id":"2402.01613","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01613","created_at":"2026-05-21T14:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01613v2","created_at":"2026-05-21T14:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01613","created_at":"2026-05-21T14:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"YENANHR4AIWZ","created_at":"2026-05-21T14:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"YENANHR4AIWZ4TXA","created_at":"2026-05-21T14:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"YENANHR4","created_at":"2026-05-21T14:48:33Z"}],"graph_snapshots":[{"event_id":"sha256:938f21450ce9cd3f684b65778b45cbd8330f07cbacb85ace378030743376b5eb","target":"graph","created_at":"2026-05-21T14:48:33Z","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/2402.01613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This technical report describes the training of nomic-embed-text-v1, the first fully reproducible, open-source, open-weights, open-data, 8192 context length English text embedding model that outperforms both OpenAI Ada-002 and OpenAI text-embedding-3-small on the short-context MTEB benchmark and the long context LoCo benchmark. We release the training code and model weights under an Apache 2.0 license. In contrast with other open-source models, we release the full curated training data and code that allows for full replication of nomic-embed-text-v1. You can find code and data to replicate the","authors_text":"Andriy Mulyar, Brandon Duderstadt, John X. Morris, Zach Nussbaum","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:18Z","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01613","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":"sha256:9ac0167815827eeb621be79b5ee2fb2ebe8f806ec52ac81ae61a270bbec81094","target":"record","created_at":"2026-05-21T14:48:33Z","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":"dcbe79f403641e164a2f430654bc7f0e1f024041db5a71cff266e71081b5882e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:18Z","title_canon_sha256":"5078e01958947bdafeafc2534defbc5622802935ef6fdb1806bb4a73ece2d769"},"schema_version":"1.0","source":{"id":"2402.01613","kind":"arxiv","version":2}},"canonical_sha256":"c11a069e3c022d9e4ee0b0e64e3a85a2f2ac3d79fb38f77adad5e5204af58fc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c11a069e3c022d9e4ee0b0e64e3a85a2f2ac3d79fb38f77adad5e5204af58fc4","first_computed_at":"2026-05-21T14:48:33.905059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T14:48:33.905059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pu5x6+WtU2YaBYBlRs3RrvKmJmqlHXewtkMu0gbAHZ4geOI/8su/rqsgBIcMKXYfIrIHklCql+LM6XUWscnZDg==","signature_status":"signed_v1","signed_at":"2026-05-21T14:48:33.907845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01613","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ac0167815827eeb621be79b5ee2fb2ebe8f806ec52ac81ae61a270bbec81094","sha256:938f21450ce9cd3f684b65778b45cbd8330f07cbacb85ace378030743376b5eb"],"state_sha256":"06abd81091aed2dee619773715318d4370e95493159c72fb7d1e34a714f2dc2b"}