{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TX7CYLVOG4N5XJGLEMDHJJBE3O","short_pith_number":"pith:TX7CYLVO","schema_version":"1.0","canonical_sha256":"9dfe2c2eae371bdba4cb230674a424dbbc45c20a57ba6c1d6278ec48087b5e72","source":{"kind":"arxiv","id":"2505.19624","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingjie Yan, Danli Shi, Jiancheng Yang, Meng Yuan, Mingguang He, Pusheng Xu, Weiyi Zhang, Xia Gong, Xiaolan Chen, Yalin Zheng","submitted_at":"2025-05-26T07:45:42Z","abstract_excerpt":"Purpose: To develop a bilingual multimodal visual question answering (VQA) benchmark for evaluating VLMs in ophthalmology. Methods: Ophthalmic image posts and associated captions published between January 1, 2016, and December 31, 2024, were collected from WeChat Official Accounts. Based on these captions, bilingual question-answer (QA) pairs in Chinese and English were generated using GPT-4o-mini. QA pairs were categorized into six subsets by question type and language: binary (Binary_CN, Binary_EN), single-choice (Single-choice_CN, Single-choice_EN), and open-ended (Open-ended_CN, Open-ended"},"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":"2505.19624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T07:45:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b3e09d9321cf73b40aded477e60f6f30b9ff60817dfe99756d380b4f69fbdbf","abstract_canon_sha256":"50e9c8cc876c417a43d3e02d4e0bed938fe7192d81dbe0f5954f8fbd653390ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:33.721578Z","signature_b64":"vdGeEMi9yeEiwFF1C1YWYFOratSqw4YlRqilIiEHorjB/v5lQliRlGlCLaGjYES6FOZW99W3BxHqVhwBdWswCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dfe2c2eae371bdba4cb230674a424dbbc45c20a57ba6c1d6278ec48087b5e72","last_reissued_at":"2026-07-05T11:09:33.721169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:33.721169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingjie Yan, Danli Shi, Jiancheng Yang, Meng Yuan, Mingguang He, Pusheng Xu, Weiyi Zhang, Xia Gong, Xiaolan Chen, Yalin Zheng","submitted_at":"2025-05-26T07:45:42Z","abstract_excerpt":"Purpose: To develop a bilingual multimodal visual question answering (VQA) benchmark for evaluating VLMs in ophthalmology. Methods: Ophthalmic image posts and associated captions published between January 1, 2016, and December 31, 2024, were collected from WeChat Official Accounts. Based on these captions, bilingual question-answer (QA) pairs in Chinese and English were generated using GPT-4o-mini. QA pairs were categorized into six subsets by question type and language: binary (Binary_CN, Binary_EN), single-choice (Single-choice_CN, Single-choice_EN), and open-ended (Open-ended_CN, Open-ended"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19624","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/2505.19624/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":"2505.19624","created_at":"2026-07-05T11:09:33.721220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19624v1","created_at":"2026-07-05T11:09:33.721220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19624","created_at":"2026-07-05T11:09:33.721220+00:00"},{"alias_kind":"pith_short_12","alias_value":"TX7CYLVOG4N5","created_at":"2026-07-05T11:09:33.721220+00:00"},{"alias_kind":"pith_short_16","alias_value":"TX7CYLVOG4N5XJGL","created_at":"2026-07-05T11:09:33.721220+00:00"},{"alias_kind":"pith_short_8","alias_value":"TX7CYLVO","created_at":"2026-07-05T11:09:33.721220+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/TX7CYLVOG4N5XJGLEMDHJJBE3O","json":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O.json","graph_json":"https://pith.science/api/pith-number/TX7CYLVOG4N5XJGLEMDHJJBE3O/graph.json","events_json":"https://pith.science/api/pith-number/TX7CYLVOG4N5XJGLEMDHJJBE3O/events.json","paper":"https://pith.science/paper/TX7CYLVO"},"agent_actions":{"view_html":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O","download_json":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O.json","view_paper":"https://pith.science/paper/TX7CYLVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19624&json=true","fetch_graph":"https://pith.science/api/pith-number/TX7CYLVOG4N5XJGLEMDHJJBE3O/graph.json","fetch_events":"https://pith.science/api/pith-number/TX7CYLVOG4N5XJGLEMDHJJBE3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O/action/storage_attestation","attest_author":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O/action/author_attestation","sign_citation":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O/action/citation_signature","submit_replication":"https://pith.science/pith/TX7CYLVOG4N5XJGLEMDHJJBE3O/action/replication_record"}},"created_at":"2026-07-05T11:09:33.721220+00:00","updated_at":"2026-07-05T11:09:33.721220+00:00"}