{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MEJZ5NUW4L7QKJO62E47GGSFZF","short_pith_number":"pith:MEJZ5NUW","schema_version":"1.0","canonical_sha256":"61139eb696e2ff0525ded139f31a45c9673ccbaac65d0ac576b03bcfd72f0b9d","source":{"kind":"arxiv","id":"2504.14692","version":1},"attestation_state":"computed","paper":{"title":"OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohan Lei, Jian Wu, Jimeng Sun, Sibo Song, Songtao Jiang, Yan Zhang, Yuan Wang, Zijie Meng, Zuozhu Liu","submitted_at":"2025-04-20T17:53:56Z","abstract_excerpt":"The practical deployment of medical vision-language models (Med-VLMs) necessitates seamless integration of textual data with diverse visual modalities, including 2D/3D images and videos, yet existing models typically employ separate encoders for different modalities. To address this limitation, we present OmniV-Med, a unified framework for multimodal medical understanding. Our technical contributions are threefold: First, we construct OmniV-Med-Instruct, a comprehensive multimodal medical dataset containing 252K instructional samples spanning 14 medical image modalities and 11 clinical tasks. "},"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":"2504.14692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T17:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"91990585c16172dbf2a8b3ccf9a2f1a4476262bcfca55d2b0e562c2729eef5a8","abstract_canon_sha256":"f890cb8b8c1220df91e617de5a2caf98e163e6ae59350f7807740e8ec1f46a7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:49.166991Z","signature_b64":"4hbhGvmocxJn8j2a7YKbDK7oW6eSO85VlJZfc6pvQtAIW2PuvWfkzwrjkSGBfb1zVejCRbesms3e1B240e8kBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61139eb696e2ff0525ded139f31a45c9673ccbaac65d0ac576b03bcfd72f0b9d","last_reissued_at":"2026-07-05T10:51:49.166418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:49.166418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohan Lei, Jian Wu, Jimeng Sun, Sibo Song, Songtao Jiang, Yan Zhang, Yuan Wang, Zijie Meng, Zuozhu Liu","submitted_at":"2025-04-20T17:53:56Z","abstract_excerpt":"The practical deployment of medical vision-language models (Med-VLMs) necessitates seamless integration of textual data with diverse visual modalities, including 2D/3D images and videos, yet existing models typically employ separate encoders for different modalities. To address this limitation, we present OmniV-Med, a unified framework for multimodal medical understanding. Our technical contributions are threefold: First, we construct OmniV-Med-Instruct, a comprehensive multimodal medical dataset containing 252K instructional samples spanning 14 medical image modalities and 11 clinical tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14692","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/2504.14692/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":"2504.14692","created_at":"2026-07-05T10:51:49.166482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14692v1","created_at":"2026-07-05T10:51:49.166482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14692","created_at":"2026-07-05T10:51:49.166482+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEJZ5NUW4L7Q","created_at":"2026-07-05T10:51:49.166482+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEJZ5NUW4L7QKJO6","created_at":"2026-07-05T10:51:49.166482+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEJZ5NUW","created_at":"2026-07-05T10:51:49.166482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01751","citing_title":"MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":235,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31292","citing_title":"AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF","json":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF.json","graph_json":"https://pith.science/api/pith-number/MEJZ5NUW4L7QKJO62E47GGSFZF/graph.json","events_json":"https://pith.science/api/pith-number/MEJZ5NUW4L7QKJO62E47GGSFZF/events.json","paper":"https://pith.science/paper/MEJZ5NUW"},"agent_actions":{"view_html":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF","download_json":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF.json","view_paper":"https://pith.science/paper/MEJZ5NUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14692&json=true","fetch_graph":"https://pith.science/api/pith-number/MEJZ5NUW4L7QKJO62E47GGSFZF/graph.json","fetch_events":"https://pith.science/api/pith-number/MEJZ5NUW4L7QKJO62E47GGSFZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF/action/storage_attestation","attest_author":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF/action/author_attestation","sign_citation":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF/action/citation_signature","submit_replication":"https://pith.science/pith/MEJZ5NUW4L7QKJO62E47GGSFZF/action/replication_record"}},"created_at":"2026-07-05T10:51:49.166482+00:00","updated_at":"2026-07-05T10:51:49.166482+00:00"}