{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CKRGY6RZ7XTYPW7ZEC2FI5AAQU","short_pith_number":"pith:CKRGY6RZ","schema_version":"1.0","canonical_sha256":"12a26c7a39fde787dbf920b4547400853c8c0fda3bd8f1dbe8043e550d01f769","source":{"kind":"arxiv","id":"2605.22414","version":1},"attestation_state":"computed","paper":{"title":"Towards Clinically Interpretable Ophthalmic VQA via Spatially-Grounded Lesion Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Liu, Chengcheng Zhu, Huazhu Fu, Jiang Liu, Meng Wang, Xingyue Wang, Zhixuan Zhang","submitted_at":"2026-05-21T12:37:03Z","abstract_excerpt":"Visual Question Answering (VQA) holds great promise for clinical support, particularly in ophthalmology, where retinal fundus photography is essential for diagnosis. However, ophthalmic VQA benchmarks primarily emphasize answer accuracy, neglecting the explicit visual evidence necessary for clinical interpretability. In this work, we introduce FundusGround, a new benchmark for clinically interpretable ophthalmic VQA with spatially-grounded lesion evidence. Specifically, we propose a three-stage pipeline that collects 10,719 fundus images with 15,595 image-level meticulously annotated lesions. "},"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":"2605.22414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T12:37:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba391594f49aba608f445ab1fb9fc2df2271726a3f8a8ace331d35c0d2853933","abstract_canon_sha256":"9f01e89f401d74ab14ef503687e443c025f00149f00c7496c11b8ecddbbb70de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:42.251478Z","signature_b64":"ak3lrC7dRSc+FATnBIFQ9SHOQ6JSySMzvPCNHL2S7MwwhW4mvT4yAIXuaEZjjg9zA7V1hzTMdhiJO1Op+8YXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12a26c7a39fde787dbf920b4547400853c8c0fda3bd8f1dbe8043e550d01f769","last_reissued_at":"2026-05-22T01:04:42.250997Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:42.250997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Clinically Interpretable Ophthalmic VQA via Spatially-Grounded Lesion Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Liu, Chengcheng Zhu, Huazhu Fu, Jiang Liu, Meng Wang, Xingyue Wang, Zhixuan Zhang","submitted_at":"2026-05-21T12:37:03Z","abstract_excerpt":"Visual Question Answering (VQA) holds great promise for clinical support, particularly in ophthalmology, where retinal fundus photography is essential for diagnosis. However, ophthalmic VQA benchmarks primarily emphasize answer accuracy, neglecting the explicit visual evidence necessary for clinical interpretability. In this work, we introduce FundusGround, a new benchmark for clinically interpretable ophthalmic VQA with spatially-grounded lesion evidence. Specifically, we propose a three-stage pipeline that collects 10,719 fundus images with 15,595 image-level meticulously annotated lesions. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22414","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/2605.22414/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":"2605.22414","created_at":"2026-05-22T01:04:42.251069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22414v1","created_at":"2026-05-22T01:04:42.251069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22414","created_at":"2026-05-22T01:04:42.251069+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKRGY6RZ7XTY","created_at":"2026-05-22T01:04:42.251069+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKRGY6RZ7XTYPW7Z","created_at":"2026-05-22T01:04:42.251069+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKRGY6RZ","created_at":"2026-05-22T01:04:42.251069+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/CKRGY6RZ7XTYPW7ZEC2FI5AAQU","json":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU.json","graph_json":"https://pith.science/api/pith-number/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/graph.json","events_json":"https://pith.science/api/pith-number/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/events.json","paper":"https://pith.science/paper/CKRGY6RZ"},"agent_actions":{"view_html":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU","download_json":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU.json","view_paper":"https://pith.science/paper/CKRGY6RZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22414&json=true","fetch_graph":"https://pith.science/api/pith-number/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/graph.json","fetch_events":"https://pith.science/api/pith-number/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/action/storage_attestation","attest_author":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/action/author_attestation","sign_citation":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/action/citation_signature","submit_replication":"https://pith.science/pith/CKRGY6RZ7XTYPW7ZEC2FI5AAQU/action/replication_record"}},"created_at":"2026-05-22T01:04:42.251069+00:00","updated_at":"2026-05-22T01:04:42.251069+00:00"}