{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYPVRWW6F5P4JO5FEV7OWETKGP","short_pith_number":"pith:YYPVRWW6","schema_version":"1.0","canonical_sha256":"c61f58dade2f5fc4bba5257eeb126a33f2808bdc4c7d990c2fd7ad910bf70174","source":{"kind":"arxiv","id":"2507.01278","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Large Language Models for Multimodal Simulated Ophthalmic Decision-Making in Diabetic Retinopathy and Glaucoma Screening","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caio Regatieri, Carolina Gracitelli, Cindy Lie Tabuse, David Restepo, Fernando Korn Malerbi, Luis Filipe Nakayama","submitted_at":"2025-07-02T01:35:59Z","abstract_excerpt":"Large language models (LLMs) can simulate clinical reasoning based on natural language prompts, but their utility in ophthalmology is largely unexplored. This study evaluated GPT-4's ability to interpret structured textual descriptions of retinal fundus photographs and simulate clinical decisions for diabetic retinopathy (DR) and glaucoma screening, including the impact of adding real or synthetic clinical metadata. We conducted a retrospective diagnostic validation study using 300 annotated fundus images. GPT-4 received structured prompts describing each image, with or without patient metadat"},"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":"2507.01278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T01:35:59Z","cross_cats_sorted":[],"title_canon_sha256":"75e31a478fb8e5f24682e8b0918255079a8fa919c5b86497fc469779908b3b6d","abstract_canon_sha256":"060cf077597dd59b66d6d1ad7ab82a5620c2f208a47e7a01d5be32dd073c4b22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:27.982686Z","signature_b64":"HS53FTFVEehx6LsPlM6ZQklQPyavJfICCKDxzn9GkTnLIOD5iyBbvwZuNLsmjXdYUaS+Tp5x2v0dSqVAiugLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61f58dade2f5fc4bba5257eeb126a33f2808bdc4c7d990c2fd7ad910bf70174","last_reissued_at":"2026-07-05T11:30:27.982214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:27.982214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models for Multimodal Simulated Ophthalmic Decision-Making in Diabetic Retinopathy and Glaucoma Screening","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caio Regatieri, Carolina Gracitelli, Cindy Lie Tabuse, David Restepo, Fernando Korn Malerbi, Luis Filipe Nakayama","submitted_at":"2025-07-02T01:35:59Z","abstract_excerpt":"Large language models (LLMs) can simulate clinical reasoning based on natural language prompts, but their utility in ophthalmology is largely unexplored. This study evaluated GPT-4's ability to interpret structured textual descriptions of retinal fundus photographs and simulate clinical decisions for diabetic retinopathy (DR) and glaucoma screening, including the impact of adding real or synthetic clinical metadata. We conducted a retrospective diagnostic validation study using 300 annotated fundus images. GPT-4 received structured prompts describing each image, with or without patient metadat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01278","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/2507.01278/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":"2507.01278","created_at":"2026-07-05T11:30:27.982274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01278v1","created_at":"2026-07-05T11:30:27.982274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01278","created_at":"2026-07-05T11:30:27.982274+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYPVRWW6F5P4","created_at":"2026-07-05T11:30:27.982274+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYPVRWW6F5P4JO5F","created_at":"2026-07-05T11:30:27.982274+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYPVRWW6","created_at":"2026-07-05T11:30:27.982274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07651","citing_title":"An Agentic AI Framework Overcomes Fundamental Limitations of Large Language Models for Glaucoma Detection from Fundus Photography","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP","json":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP.json","graph_json":"https://pith.science/api/pith-number/YYPVRWW6F5P4JO5FEV7OWETKGP/graph.json","events_json":"https://pith.science/api/pith-number/YYPVRWW6F5P4JO5FEV7OWETKGP/events.json","paper":"https://pith.science/paper/YYPVRWW6"},"agent_actions":{"view_html":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP","download_json":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP.json","view_paper":"https://pith.science/paper/YYPVRWW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01278&json=true","fetch_graph":"https://pith.science/api/pith-number/YYPVRWW6F5P4JO5FEV7OWETKGP/graph.json","fetch_events":"https://pith.science/api/pith-number/YYPVRWW6F5P4JO5FEV7OWETKGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP/action/storage_attestation","attest_author":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP/action/author_attestation","sign_citation":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP/action/citation_signature","submit_replication":"https://pith.science/pith/YYPVRWW6F5P4JO5FEV7OWETKGP/action/replication_record"}},"created_at":"2026-07-05T11:30:27.982274+00:00","updated_at":"2026-07-05T11:30:27.982274+00:00"}