{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OJSKM6DSP6AAPUP5UCTOXSFUKO","short_pith_number":"pith:OJSKM6DS","schema_version":"1.0","canonical_sha256":"7264a678727f8007d1fda0a6ebc8b4538079c53fa514b6df7f45a89795103fcd","source":{"kind":"arxiv","id":"2607.04344","version":1},"attestation_state":"computed","paper":{"title":"IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dasen Dai, Hao Wei, Minqing Zhang, Wenjin Qi, Wu Yuan","submitted_at":"2026-07-05T14:59:32Z","abstract_excerpt":"While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular surface diseases (OSDs) is severely hindered by a paucity of high-fidelity, multimodal instruction-tuning data. To dismantle this data bottleneck, we introduce IRIS, an Intelligent Recognition and Interaction System tailored for fine-grained OSD understanding via external eye photography. First, we curate IRIS-120K, the largest and most comprehensive OSD visual question-answering (VQA) dataset to date. Crucially, to overcome the semantic shallowness"},"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":"2607.04344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T14:59:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8651d8702f9288d3d0ef64b4434cf0911b0bae42de5d76078d89893d2e28323","abstract_canon_sha256":"0fe78e1c4ddb9bd365fe47e734b560796e2c7959ebdccdb6ad7d732b513bdcfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:10.051026Z","signature_b64":"bfTcedKCMCy0ke85YoWfkP/MmnadYVCnXDLe5OKxVKOZCtsv0zdIQZQej4UL55A5B87TDMBJln/ceQlVqEbzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7264a678727f8007d1fda0a6ebc8b4538079c53fa514b6df7f45a89795103fcd","last_reissued_at":"2026-07-07T02:19:10.050351Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:10.050351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dasen Dai, Hao Wei, Minqing Zhang, Wenjin Qi, Wu Yuan","submitted_at":"2026-07-05T14:59:32Z","abstract_excerpt":"While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular surface diseases (OSDs) is severely hindered by a paucity of high-fidelity, multimodal instruction-tuning data. To dismantle this data bottleneck, we introduce IRIS, an Intelligent Recognition and Interaction System tailored for fine-grained OSD understanding via external eye photography. First, we curate IRIS-120K, the largest and most comprehensive OSD visual question-answering (VQA) dataset to date. Crucially, to overcome the semantic shallowness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04344","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/2607.04344/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":"2607.04344","created_at":"2026-07-07T02:19:10.050455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04344v1","created_at":"2026-07-07T02:19:10.050455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04344","created_at":"2026-07-07T02:19:10.050455+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJSKM6DSP6AA","created_at":"2026-07-07T02:19:10.050455+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJSKM6DSP6AAPUP5","created_at":"2026-07-07T02:19:10.050455+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJSKM6DS","created_at":"2026-07-07T02:19:10.050455+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/OJSKM6DSP6AAPUP5UCTOXSFUKO","json":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO.json","graph_json":"https://pith.science/api/pith-number/OJSKM6DSP6AAPUP5UCTOXSFUKO/graph.json","events_json":"https://pith.science/api/pith-number/OJSKM6DSP6AAPUP5UCTOXSFUKO/events.json","paper":"https://pith.science/paper/OJSKM6DS"},"agent_actions":{"view_html":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO","download_json":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO.json","view_paper":"https://pith.science/paper/OJSKM6DS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04344&json=true","fetch_graph":"https://pith.science/api/pith-number/OJSKM6DSP6AAPUP5UCTOXSFUKO/graph.json","fetch_events":"https://pith.science/api/pith-number/OJSKM6DSP6AAPUP5UCTOXSFUKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO/action/storage_attestation","attest_author":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO/action/author_attestation","sign_citation":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO/action/citation_signature","submit_replication":"https://pith.science/pith/OJSKM6DSP6AAPUP5UCTOXSFUKO/action/replication_record"}},"created_at":"2026-07-07T02:19:10.050455+00:00","updated_at":"2026-07-07T02:19:10.050455+00:00"}