{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WPCAJ6DV6ASGFLWKEIHKCFJRBF","short_pith_number":"pith:WPCAJ6DV","schema_version":"1.0","canonical_sha256":"b3c404f875f02462aeca220ea1153109583398c028696f5af4c730b9ae3763f0","source":{"kind":"arxiv","id":"2410.20327","version":5},"attestation_state":"computed","paper":{"title":"R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiaxiang Liu, Kangrui Ruan, Shichu Chen, Xupeng Chen, Zhixin Lai, Zuozhu Liu","submitted_at":"2024-10-27T03:56:56Z","abstract_excerpt":"Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual reg"},"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":"2410.20327","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T03:56:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b45265dba1bad9bcc885a0011293c3b41d33cb85b3b734067a4eb893ab80cca0","abstract_canon_sha256":"e596c6beb40d2d0aa709cfe7f2685cbb69d4b0f21ab1b4caf1f5f422d0af1810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:18.336521Z","signature_b64":"oiahQ1DbLg40gTcyp2o2V/os/P9Oo2m1XAPtt65S7Ue8gRg71DwZnhVrfbJXfuA+UqiGoKjcHqipNnMaEFXoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3c404f875f02462aeca220ea1153109583398c028696f5af4c730b9ae3763f0","last_reissued_at":"2026-07-05T10:27:18.335859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:18.335859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiaxiang Liu, Kangrui Ruan, Shichu Chen, Xupeng Chen, Zhixin Lai, Zuozhu Liu","submitted_at":"2024-10-27T03:56:56Z","abstract_excerpt":"Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20327","kind":"arxiv","version":5},"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/2410.20327/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":"2410.20327","created_at":"2026-07-05T10:27:18.335928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20327v5","created_at":"2026-07-05T10:27:18.335928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20327","created_at":"2026-07-05T10:27:18.335928+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPCAJ6DV6ASG","created_at":"2026-07-05T10:27:18.335928+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPCAJ6DV6ASGFLWK","created_at":"2026-07-05T10:27:18.335928+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPCAJ6DV","created_at":"2026-07-05T10:27:18.335928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01911","citing_title":"SurgCheck: Do Vision-Language Models Really Look at Images in Surgical VQA?","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09887","citing_title":"SemEnrich: Self-Supervised Semantic Enrichment of Radiology Reports for Vision-Language Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04064","citing_title":"Improving Medical VQA through Trajectory-Aware Process Supervision","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF","json":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF.json","graph_json":"https://pith.science/api/pith-number/WPCAJ6DV6ASGFLWKEIHKCFJRBF/graph.json","events_json":"https://pith.science/api/pith-number/WPCAJ6DV6ASGFLWKEIHKCFJRBF/events.json","paper":"https://pith.science/paper/WPCAJ6DV"},"agent_actions":{"view_html":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF","download_json":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF.json","view_paper":"https://pith.science/paper/WPCAJ6DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20327&json=true","fetch_graph":"https://pith.science/api/pith-number/WPCAJ6DV6ASGFLWKEIHKCFJRBF/graph.json","fetch_events":"https://pith.science/api/pith-number/WPCAJ6DV6ASGFLWKEIHKCFJRBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF/action/storage_attestation","attest_author":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF/action/author_attestation","sign_citation":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF/action/citation_signature","submit_replication":"https://pith.science/pith/WPCAJ6DV6ASGFLWKEIHKCFJRBF/action/replication_record"}},"created_at":"2026-07-05T10:27:18.335928+00:00","updated_at":"2026-07-05T10:27:18.335928+00:00"}