{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UL2MFPJZ2UTMGYQEXEXHJPU2VU","short_pith_number":"pith:UL2MFPJZ","schema_version":"1.0","canonical_sha256":"a2f4c2bd39d526c36204b92e74be9aad312a09ad8fbfbfc37c2408ad34549dad","source":{"kind":"arxiv","id":"2406.18587","version":1},"attestation_state":"computed","paper":{"title":"Nomic Embed Vision: Expanding the Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Andriy Mulyar, Brandon Duderstadt, Zach Nussbaum","submitted_at":"2024-06-06T21:02:51Z","abstract_excerpt":"This technical report describes the training of nomic-embed-vision, a highly performant, open-code, open-weights image embedding model that shares the same latent space as nomic-embed-text. Together, nomic-embed-vision and nomic-embed-text form the first unified latent space to achieve high performance across vision, language, and multimodal tasks."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.18587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T21:02:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1aaa8f8c2cc20688ce3ad540b18a74d6878c20b57fa6c18a269a721e4291d9a4","abstract_canon_sha256":"887101c3cfee675350f24e4ecfce8c0a7fdc85f2f79e8de557e36b45ee7b5e40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:22.944312Z","signature_b64":"3H+lO0OwU7uDzUPSCTroIHfpnlamaankfqo8IihOHgtzMVyduCYh3EorH/8X2n5qYRstjGHm92pLKZLiuw1GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f4c2bd39d526c36204b92e74be9aad312a09ad8fbfbfc37c2408ad34549dad","last_reissued_at":"2026-07-05T08:37:22.943880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:22.943880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nomic Embed Vision: Expanding the Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Andriy Mulyar, Brandon Duderstadt, Zach Nussbaum","submitted_at":"2024-06-06T21:02:51Z","abstract_excerpt":"This technical report describes the training of nomic-embed-vision, a highly performant, open-code, open-weights image embedding model that shares the same latent space as nomic-embed-text. Together, nomic-embed-vision and nomic-embed-text form the first unified latent space to achieve high performance across vision, language, and multimodal tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18587","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/2406.18587/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.18587","created_at":"2026-07-05T08:37:22.943947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18587v1","created_at":"2026-07-05T08:37:22.943947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18587","created_at":"2026-07-05T08:37:22.943947+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL2MFPJZ2UTM","created_at":"2026-07-05T08:37:22.943947+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL2MFPJZ2UTMGYQE","created_at":"2026-07-05T08:37:22.943947+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL2MFPJZ","created_at":"2026-07-05T08:37:22.943947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23539","citing_title":"LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08384","citing_title":"jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07584","citing_title":"Multimodal Contextualized Support for Enhancing Video Retrieval System","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08384","citing_title":"jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08384","citing_title":"jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07220","citing_title":"HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21893","citing_title":"Revealing Geography-Driven Signals in Zone-Level Claim Frequency Models: An Empirical Study using Environmental and Visual Predictors","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU","json":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU.json","graph_json":"https://pith.science/api/pith-number/UL2MFPJZ2UTMGYQEXEXHJPU2VU/graph.json","events_json":"https://pith.science/api/pith-number/UL2MFPJZ2UTMGYQEXEXHJPU2VU/events.json","paper":"https://pith.science/paper/UL2MFPJZ"},"agent_actions":{"view_html":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU","download_json":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU.json","view_paper":"https://pith.science/paper/UL2MFPJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18587&json=true","fetch_graph":"https://pith.science/api/pith-number/UL2MFPJZ2UTMGYQEXEXHJPU2VU/graph.json","fetch_events":"https://pith.science/api/pith-number/UL2MFPJZ2UTMGYQEXEXHJPU2VU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU/action/storage_attestation","attest_author":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU/action/author_attestation","sign_citation":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU/action/citation_signature","submit_replication":"https://pith.science/pith/UL2MFPJZ2UTMGYQEXEXHJPU2VU/action/replication_record"}},"created_at":"2026-07-05T08:37:22.943947+00:00","updated_at":"2026-07-05T08:37:22.943947+00:00"}