{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GZWHAUC5ZP5SHMSOA3QVWXAMRI","short_pith_number":"pith:GZWHAUC5","schema_version":"1.0","canonical_sha256":"366c70505dcbfb23b24e06e15b5c0c8a10a293ff74230f52850efc4260e40565","source":{"kind":"arxiv","id":"2408.02865","version":2},"attestation_state":"computed","paper":{"title":"VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"eess.IV","authors_text":"Deming Wang, Diping Song, Fei Li, Paul E. Kinahan, Xiulan Zhang, Yu Qiao, Zefeng Yang, Zihan Li","submitted_at":"2024-08-05T23:31:07Z","abstract_excerpt":"The need for improved diagnostic methods in ophthalmology is acute, especially in the underdeveloped regions with limited access to specialists and advanced equipment. Therefore, we introduce VisionUnite, a novel vision-language foundation model for ophthalmology enhanced with clinical knowledge. VisionUnite has been pretrained on an extensive dataset comprising 1.24 million image-text pairs, and further refined using our proposed MMFundus dataset, which includes 296,379 high-quality fundus image-text pairs and 889,137 simulated doctor-patient dialogue instances. Our experiments indicate that "},"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":"2408.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-08-05T23:31:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"562564f91320191bf76aa79fb3a1b25ff88792da0b55616cd690113513c365ee","abstract_canon_sha256":"727baf6dd387bce40790013262ac2435d77fa44be71284235a5146223dbb8bdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:13.877086Z","signature_b64":"cRziRVYrAKR/ZiwXM7z6rPQgr8o+kmjjRmj8IFuoJBhjTAXZyPmWuA682ZeCDuPfOueDpOlrSXMT9Xy/jYg1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"366c70505dcbfb23b24e06e15b5c0c8a10a293ff74230f52850efc4260e40565","last_reissued_at":"2026-07-05T11:52:13.876409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:13.876409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"eess.IV","authors_text":"Deming Wang, Diping Song, Fei Li, Paul E. Kinahan, Xiulan Zhang, Yu Qiao, Zefeng Yang, Zihan Li","submitted_at":"2024-08-05T23:31:07Z","abstract_excerpt":"The need for improved diagnostic methods in ophthalmology is acute, especially in the underdeveloped regions with limited access to specialists and advanced equipment. Therefore, we introduce VisionUnite, a novel vision-language foundation model for ophthalmology enhanced with clinical knowledge. VisionUnite has been pretrained on an extensive dataset comprising 1.24 million image-text pairs, and further refined using our proposed MMFundus dataset, which includes 296,379 high-quality fundus image-text pairs and 889,137 simulated doctor-patient dialogue instances. Our experiments indicate that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02865","kind":"arxiv","version":2},"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/2408.02865/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":"2408.02865","created_at":"2026-07-05T11:52:13.876565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02865v2","created_at":"2026-07-05T11:52:13.876565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02865","created_at":"2026-07-05T11:52:13.876565+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZWHAUC5ZP5S","created_at":"2026-07-05T11:52:13.876565+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZWHAUC5ZP5SHMSO","created_at":"2026-07-05T11:52:13.876565+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZWHAUC5","created_at":"2026-07-05T11:52:13.876565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17539","citing_title":"Constructing Ophthalmic MLLM for Positioning-diagnosis Collaboration Through Clinical Cognitive Chain Reasoning","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI","json":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI.json","graph_json":"https://pith.science/api/pith-number/GZWHAUC5ZP5SHMSOA3QVWXAMRI/graph.json","events_json":"https://pith.science/api/pith-number/GZWHAUC5ZP5SHMSOA3QVWXAMRI/events.json","paper":"https://pith.science/paper/GZWHAUC5"},"agent_actions":{"view_html":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI","download_json":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI.json","view_paper":"https://pith.science/paper/GZWHAUC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02865&json=true","fetch_graph":"https://pith.science/api/pith-number/GZWHAUC5ZP5SHMSOA3QVWXAMRI/graph.json","fetch_events":"https://pith.science/api/pith-number/GZWHAUC5ZP5SHMSOA3QVWXAMRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI/action/storage_attestation","attest_author":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI/action/author_attestation","sign_citation":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI/action/citation_signature","submit_replication":"https://pith.science/pith/GZWHAUC5ZP5SHMSOA3QVWXAMRI/action/replication_record"}},"created_at":"2026-07-05T11:52:13.876565+00:00","updated_at":"2026-07-05T11:52:13.876565+00:00"}