{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAVHU77G5H7LMZWK7ZJYROHFWT","short_pith_number":"pith:EAVHU77G","schema_version":"1.0","canonical_sha256":"202a7a7fe6e9feb666cafe5388b8e5b4e452bbb8ac795cc9f348f9b33668ae12","source":{"kind":"arxiv","id":"2405.14137","version":2},"attestation_state":"computed","paper":{"title":"RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanruo Liu, Huiqi Li, Jia Guo, Jiawei Du, Ningli Wang, Shengzhu Yang, Weihang Zhang","submitted_at":"2024-05-23T03:20:51Z","abstract_excerpt":"The Vision-Language Foundation model is increasingly investigated in the fields of computer vision and natural language processing, yet its exploration in ophthalmology and broader medical applications remains limited. The challenge is the lack of labeled data for the training of foundation model. To handle this issue, a CLIP-style retinal image foundation model is developed in this paper. Our foundation model, RET-CLIP, is specifically trained on a dataset of 193,865 patients to extract general features of color fundus photographs (CFPs), employing a tripartite optimization strategy to focus "},"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":"2405.14137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T03:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"22a25e6b7586133de9c292f52aca45d51937fe0a78d6a02cbe61151b32acfb2f","abstract_canon_sha256":"86cde219754ecb77a85e82f9c62564c8864eb3af8132312162df3d290f72df31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:20.118427Z","signature_b64":"oVGTLFTCgExMUt3MjxONmExpxPoI2ekXQeCjnGyBGsas7gbct/CNnvsZSg/ZBoK0h+L22G4cE9lAdsctm8x1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"202a7a7fe6e9feb666cafe5388b8e5b4e452bbb8ac795cc9f348f9b33668ae12","last_reissued_at":"2026-07-05T08:56:20.118007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:20.118007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanruo Liu, Huiqi Li, Jia Guo, Jiawei Du, Ningli Wang, Shengzhu Yang, Weihang Zhang","submitted_at":"2024-05-23T03:20:51Z","abstract_excerpt":"The Vision-Language Foundation model is increasingly investigated in the fields of computer vision and natural language processing, yet its exploration in ophthalmology and broader medical applications remains limited. The challenge is the lack of labeled data for the training of foundation model. To handle this issue, a CLIP-style retinal image foundation model is developed in this paper. Our foundation model, RET-CLIP, is specifically trained on a dataset of 193,865 patients to extract general features of color fundus photographs (CFPs), employing a tripartite optimization strategy to focus "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14137","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/2405.14137/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":"2405.14137","created_at":"2026-07-05T08:56:20.118069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14137v2","created_at":"2026-07-05T08:56:20.118069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14137","created_at":"2026-07-05T08:56:20.118069+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAVHU77G5H7L","created_at":"2026-07-05T08:56:20.118069+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAVHU77G5H7LMZWK","created_at":"2026-07-05T08:56:20.118069+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAVHU77G","created_at":"2026-07-05T08:56:20.118069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19522","citing_title":"REVEAL++: Differentiable Phenotypic Grouping for Vision-Language Retinal Modeling of Alzheimer's Disease Risk","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03806","citing_title":"Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09242","citing_title":"Cross-Modal Semantic-Enhanced Diffusion Framework for Diabetic Retinopathy Grading","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18757","citing_title":"REVEAL: Multimodal Vision-Language Alignment of Retinal Morphometry and Clinical Risks for Incident AD and Dementia Prediction","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT","json":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT.json","graph_json":"https://pith.science/api/pith-number/EAVHU77G5H7LMZWK7ZJYROHFWT/graph.json","events_json":"https://pith.science/api/pith-number/EAVHU77G5H7LMZWK7ZJYROHFWT/events.json","paper":"https://pith.science/paper/EAVHU77G"},"agent_actions":{"view_html":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT","download_json":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT.json","view_paper":"https://pith.science/paper/EAVHU77G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14137&json=true","fetch_graph":"https://pith.science/api/pith-number/EAVHU77G5H7LMZWK7ZJYROHFWT/graph.json","fetch_events":"https://pith.science/api/pith-number/EAVHU77G5H7LMZWK7ZJYROHFWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT/action/storage_attestation","attest_author":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT/action/author_attestation","sign_citation":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT/action/citation_signature","submit_replication":"https://pith.science/pith/EAVHU77G5H7LMZWK7ZJYROHFWT/action/replication_record"}},"created_at":"2026-07-05T08:56:20.118069+00:00","updated_at":"2026-07-05T08:56:20.118069+00:00"}