{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ISHXJXIELT5CXBVNBSKBK7SONP","short_pith_number":"pith:ISHXJXIE","schema_version":"1.0","canonical_sha256":"448f74dd045cfa2b86ad0c94157e4e6bc258a1b0a6c83e6616a328c23587eaec","source":{"kind":"arxiv","id":"2503.03987","version":1},"attestation_state":"computed","paper":{"title":"RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Natasha Lepore, Oana Dumitrascu, Peijie Qiu, Vamsi Krishna Vasa, Wenhui Zhu, Xin Li, Xiwen Chen, Xuanzhao Dong, Yalin Wang, Yanxi Chen, Yi Su","submitted_at":"2025-03-06T00:19:54Z","abstract_excerpt":"Recently, Multimodal Large Language Models (MLLMs) have gained significant attention for their remarkable ability to process and analyze non-textual data, such as images, videos, and audio. Notably, several adaptations of general-domain MLLMs to the medical field have been explored, including LLaVA-Med. However, these medical adaptations remain insufficiently advanced in understanding and interpreting retinal images. In contrast, medical experts emphasize the importance of quantitative analyses for disease detection and interpretation. This underscores a gap between general-domain and medical-"},"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":"2503.03987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T00:19:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"028b697c43dd28669f328feb297639b52249806cea396bbdc5ab31de3c269755","abstract_canon_sha256":"781196e5f7b24af9698cf3ae7e59e4bee2598ea64f883c0edf406aae54802426"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:25.954582Z","signature_b64":"+D0EF/tyba8lu+9n+CTkFNC9QwOitS1TpIOJid20viAyYvLpcSXvZl9KLusg3IVVJULH6fc5M4CA2vTxJ5NRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"448f74dd045cfa2b86ad0c94157e4e6bc258a1b0a6c83e6616a328c23587eaec","last_reissued_at":"2026-07-05T10:25:25.954077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:25.954077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Natasha Lepore, Oana Dumitrascu, Peijie Qiu, Vamsi Krishna Vasa, Wenhui Zhu, Xin Li, Xiwen Chen, Xuanzhao Dong, Yalin Wang, Yanxi Chen, Yi Su","submitted_at":"2025-03-06T00:19:54Z","abstract_excerpt":"Recently, Multimodal Large Language Models (MLLMs) have gained significant attention for their remarkable ability to process and analyze non-textual data, such as images, videos, and audio. Notably, several adaptations of general-domain MLLMs to the medical field have been explored, including LLaVA-Med. However, these medical adaptations remain insufficiently advanced in understanding and interpreting retinal images. In contrast, medical experts emphasize the importance of quantitative analyses for disease detection and interpretation. This underscores a gap between general-domain and medical-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03987","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/2503.03987/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":"2503.03987","created_at":"2026-07-05T10:25:25.954138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03987v1","created_at":"2026-07-05T10:25:25.954138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03987","created_at":"2026-07-05T10:25:25.954138+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISHXJXIELT5C","created_at":"2026-07-05T10:25:25.954138+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISHXJXIELT5CXBVN","created_at":"2026-07-05T10:25:25.954138+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISHXJXIE","created_at":"2026-07-05T10:25:25.954138+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27960","citing_title":"Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08322","citing_title":"Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP","json":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP.json","graph_json":"https://pith.science/api/pith-number/ISHXJXIELT5CXBVNBSKBK7SONP/graph.json","events_json":"https://pith.science/api/pith-number/ISHXJXIELT5CXBVNBSKBK7SONP/events.json","paper":"https://pith.science/paper/ISHXJXIE"},"agent_actions":{"view_html":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP","download_json":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP.json","view_paper":"https://pith.science/paper/ISHXJXIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03987&json=true","fetch_graph":"https://pith.science/api/pith-number/ISHXJXIELT5CXBVNBSKBK7SONP/graph.json","fetch_events":"https://pith.science/api/pith-number/ISHXJXIELT5CXBVNBSKBK7SONP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP/action/storage_attestation","attest_author":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP/action/author_attestation","sign_citation":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP/action/citation_signature","submit_replication":"https://pith.science/pith/ISHXJXIELT5CXBVNBSKBK7SONP/action/replication_record"}},"created_at":"2026-07-05T10:25:25.954138+00:00","updated_at":"2026-07-05T10:25:25.954138+00:00"}