{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DM4YT2LECKZ3B3PAPNDR5G2MU6","short_pith_number":"pith:DM4YT2LE","schema_version":"1.0","canonical_sha256":"1b3989e96412b3b0ede07b471e9b4ca7a10a93942d5759cfc43052bdb68b93d2","source":{"kind":"arxiv","id":"2402.09181","version":2},"attestation_state":"computed","paper":{"title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Junjun He, Ping Luo, Quanfeng Lu, Tianbin Li, Wenqi Shao, Yu Qiao, Yutao Hu","submitted_at":"2024-02-14T13:51:56Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in various multimodal tasks. However, their potential in the medical domain remains largely unexplored. A significant challenge arises from the scarcity of diverse medical images spanning various modalities and anatomical regions, which is essential in real-world medical applications. To solve this problem, in this paper, we introduce OmniMedVQA, a novel comprehensive medical Visual Question Answering (VQA) benchmark. This benchmark is collected from 73 different medical datasets, including 12 different modalities a"},"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":"2402.09181","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.IV","submitted_at":"2024-02-14T13:51:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4d3b92a8f76c1d56ace6aee150004ed75e1a0db4ac1e3eb8db4283a447783b49","abstract_canon_sha256":"e6ab494173a5b43202a5c825a19105ff3655e93120c697c80e85a4a6a942beb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:23.727148Z","signature_b64":"aGA4v4x8FAkK0+KZIyisM7yCubeVhTPk5M5GlfaEWouVHGAxl9+jp7iaGlM+JSlGxpZK7rKlKU4WXGgDLxE4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b3989e96412b3b0ede07b471e9b4ca7a10a93942d5759cfc43052bdb68b93d2","last_reissued_at":"2026-07-05T08:10:23.726622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:23.726622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Junjun He, Ping Luo, Quanfeng Lu, Tianbin Li, Wenqi Shao, Yu Qiao, Yutao Hu","submitted_at":"2024-02-14T13:51:56Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in various multimodal tasks. However, their potential in the medical domain remains largely unexplored. A significant challenge arises from the scarcity of diverse medical images spanning various modalities and anatomical regions, which is essential in real-world medical applications. To solve this problem, in this paper, we introduce OmniMedVQA, a novel comprehensive medical Visual Question Answering (VQA) benchmark. This benchmark is collected from 73 different medical datasets, including 12 different modalities a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09181","kind":"arxiv","version":2},"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/2402.09181/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":"2402.09181","created_at":"2026-07-05T08:10:23.726679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09181v2","created_at":"2026-07-05T08:10:23.726679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09181","created_at":"2026-07-05T08:10:23.726679+00:00"},{"alias_kind":"pith_short_12","alias_value":"DM4YT2LECKZ3","created_at":"2026-07-05T08:10:23.726679+00:00"},{"alias_kind":"pith_short_16","alias_value":"DM4YT2LECKZ3B3PA","created_at":"2026-07-05T08:10:23.726679+00:00"},{"alias_kind":"pith_short_8","alias_value":"DM4YT2LE","created_at":"2026-07-05T08:10:23.726679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27023","citing_title":"Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06696","citing_title":"MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22258","citing_title":"Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10415","citing_title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6","json":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6.json","graph_json":"https://pith.science/api/pith-number/DM4YT2LECKZ3B3PAPNDR5G2MU6/graph.json","events_json":"https://pith.science/api/pith-number/DM4YT2LECKZ3B3PAPNDR5G2MU6/events.json","paper":"https://pith.science/paper/DM4YT2LE"},"agent_actions":{"view_html":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6","download_json":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6.json","view_paper":"https://pith.science/paper/DM4YT2LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09181&json=true","fetch_graph":"https://pith.science/api/pith-number/DM4YT2LECKZ3B3PAPNDR5G2MU6/graph.json","fetch_events":"https://pith.science/api/pith-number/DM4YT2LECKZ3B3PAPNDR5G2MU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6/action/storage_attestation","attest_author":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6/action/author_attestation","sign_citation":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6/action/citation_signature","submit_replication":"https://pith.science/pith/DM4YT2LECKZ3B3PAPNDR5G2MU6/action/replication_record"}},"created_at":"2026-07-05T08:10:23.726679+00:00","updated_at":"2026-07-05T08:10:23.726679+00:00"}