{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HA2IZ5V7LKG3RIAWJGCUXXIM7V","short_pith_number":"pith:HA2IZ5V7","schema_version":"1.0","canonical_sha256":"38348cf6bf5a8db8a01649854bdd0cfd4bbc238b3ecffc248ccec9392d1a9837","source":{"kind":"arxiv","id":"2505.08414","version":1},"attestation_state":"computed","paper":{"title":"An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Can Can Xue, Charumathi Sabanayagam, Ching-Yu Cheng, Ecosse Lamoureux, Jiangnan He, Jie Xu, Jost B. Jonas, Kai Yu, Lavanya Raghavan, Lee Ching Linette Phang, Ming-Chih Ho, Preeti Gupta, Qingsheng Peng, Quan V. Hoang, Rachel Shujuan Chong, Rick Siow Mong Goh, Sahil Thakur, Seang Mei Saw, Songhomitra Panda-Jonas, Tien Yin Wong, Vinay Nangia, Wei-Chi Wu, Xiaofeng Lei, Xinxing Xu, Yang Bai, Yang Zhou, Ya Xing Wang, Yih Chung Tham, Yong Liu, Zann Lee, Zhi Da Soh","submitted_at":"2025-05-13T10:13:26Z","abstract_excerpt":"Current deep learning models are mostly task specific and lack a user-friendly interface to operate. We present Meta-EyeFM, a multi-function foundation model that integrates a large language model (LLM) with vision foundation models (VFMs) for ocular disease assessment. Meta-EyeFM leverages a routing mechanism to enable accurate task-specific analysis based on text queries. Using Low Rank Adaptation, we fine-tuned our VFMs to detect ocular and systemic diseases, differentiate ocular disease severity, and identify common ocular signs. The model achieved 100% accuracy in routing fundus images to"},"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":"2505.08414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-13T10:13:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ffc01af23ca88b665c4c46e9b7276bddfd51b2858aa0d463d0769df96349e8df","abstract_canon_sha256":"ed8489fb8a62708fa282d8f6a4891091221be3e3efd3b2972ac950b9fd1fc65e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:30.242502Z","signature_b64":"ROmX1W3KQAUyM2ygBKe6xM7jSmQLfTdlP+FbscWOQ8UcTIRRTxBVCREQDHRQ9cgTgQisbY+wjHhSy/Jb7gAWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38348cf6bf5a8db8a01649854bdd0cfd4bbc238b3ecffc248ccec9392d1a9837","last_reissued_at":"2026-07-05T11:02:30.241894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:30.241894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Can Can Xue, Charumathi Sabanayagam, Ching-Yu Cheng, Ecosse Lamoureux, Jiangnan He, Jie Xu, Jost B. Jonas, Kai Yu, Lavanya Raghavan, Lee Ching Linette Phang, Ming-Chih Ho, Preeti Gupta, Qingsheng Peng, Quan V. Hoang, Rachel Shujuan Chong, Rick Siow Mong Goh, Sahil Thakur, Seang Mei Saw, Songhomitra Panda-Jonas, Tien Yin Wong, Vinay Nangia, Wei-Chi Wu, Xiaofeng Lei, Xinxing Xu, Yang Bai, Yang Zhou, Ya Xing Wang, Yih Chung Tham, Yong Liu, Zann Lee, Zhi Da Soh","submitted_at":"2025-05-13T10:13:26Z","abstract_excerpt":"Current deep learning models are mostly task specific and lack a user-friendly interface to operate. We present Meta-EyeFM, a multi-function foundation model that integrates a large language model (LLM) with vision foundation models (VFMs) for ocular disease assessment. Meta-EyeFM leverages a routing mechanism to enable accurate task-specific analysis based on text queries. Using Low Rank Adaptation, we fine-tuned our VFMs to detect ocular and systemic diseases, differentiate ocular disease severity, and identify common ocular signs. The model achieved 100% accuracy in routing fundus images to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08414","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/2505.08414/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":"2505.08414","created_at":"2026-07-05T11:02:30.241996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08414v1","created_at":"2026-07-05T11:02:30.241996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08414","created_at":"2026-07-05T11:02:30.241996+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA2IZ5V7LKG3","created_at":"2026-07-05T11:02:30.241996+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA2IZ5V7LKG3RIAW","created_at":"2026-07-05T11:02:30.241996+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA2IZ5V7","created_at":"2026-07-05T11:02:30.241996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V","json":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V.json","graph_json":"https://pith.science/api/pith-number/HA2IZ5V7LKG3RIAWJGCUXXIM7V/graph.json","events_json":"https://pith.science/api/pith-number/HA2IZ5V7LKG3RIAWJGCUXXIM7V/events.json","paper":"https://pith.science/paper/HA2IZ5V7"},"agent_actions":{"view_html":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V","download_json":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V.json","view_paper":"https://pith.science/paper/HA2IZ5V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08414&json=true","fetch_graph":"https://pith.science/api/pith-number/HA2IZ5V7LKG3RIAWJGCUXXIM7V/graph.json","fetch_events":"https://pith.science/api/pith-number/HA2IZ5V7LKG3RIAWJGCUXXIM7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V/action/storage_attestation","attest_author":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V/action/author_attestation","sign_citation":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V/action/citation_signature","submit_replication":"https://pith.science/pith/HA2IZ5V7LKG3RIAWJGCUXXIM7V/action/replication_record"}},"created_at":"2026-07-05T11:02:30.241996+00:00","updated_at":"2026-07-05T11:02:30.241996+00:00"}