{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MY44SCGG7AZZRZ2MR4CSCIJNZK","short_pith_number":"pith:MY44SCGG","schema_version":"1.0","canonical_sha256":"6639c908c6f83398e74c8f0521212dcab42a673c24509fd100b890fa63094539","source":{"kind":"arxiv","id":"2503.01863","version":1},"attestation_state":"computed","paper":{"title":"Vision Language Models in Medicine","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","eess.IV"],"primary_cat":"cs.CV","authors_text":"Angel Gabriel Adaambiik, Beria Chingnabe Kalpelbe, Wei Peng","submitted_at":"2025-02-24T22:53:22Z","abstract_excerpt":"With the advent of Vision-Language Models (VLMs), medical artificial intelligence (AI) has experienced significant technological progress and paradigm shifts. This survey provides an extensive review of recent advancements in Medical Vision-Language Models (Med-VLMs), which integrate visual and textual data to enhance healthcare outcomes. We discuss the foundational technology behind Med-VLMs, illustrating how general models are adapted for complex medical tasks, and examine their applications in healthcare. The transformative impact of Med-VLMs on clinical practice, education, and patient car"},"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":"2503.01863","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T22:53:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","eess.IV"],"title_canon_sha256":"dcba09db5639f04ce79a9b4a08bc044d5786c273c09105b6bf61556acae15352","abstract_canon_sha256":"061462a0ebef335b34058b91ed6e86a61acebc810b02131fa2bb11ef140746cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:31.322005Z","signature_b64":"k957Xo/9iGqf1FtNZqXuxTuVU9isyPVorDY6JURLF8fyp32ZV3+xTS3mQJEajLzgzobpFXufjq2cYjK/2DxSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6639c908c6f83398e74c8f0521212dcab42a673c24509fd100b890fa63094539","last_reissued_at":"2026-07-05T10:23:31.320977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:31.320977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Language Models in Medicine","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","eess.IV"],"primary_cat":"cs.CV","authors_text":"Angel Gabriel Adaambiik, Beria Chingnabe Kalpelbe, Wei Peng","submitted_at":"2025-02-24T22:53:22Z","abstract_excerpt":"With the advent of Vision-Language Models (VLMs), medical artificial intelligence (AI) has experienced significant technological progress and paradigm shifts. This survey provides an extensive review of recent advancements in Medical Vision-Language Models (Med-VLMs), which integrate visual and textual data to enhance healthcare outcomes. We discuss the foundational technology behind Med-VLMs, illustrating how general models are adapted for complex medical tasks, and examine their applications in healthcare. The transformative impact of Med-VLMs on clinical practice, education, and patient car"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01863","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/2503.01863/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":"2503.01863","created_at":"2026-07-05T10:23:31.321081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01863v1","created_at":"2026-07-05T10:23:31.321081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01863","created_at":"2026-07-05T10:23:31.321081+00:00"},{"alias_kind":"pith_short_12","alias_value":"MY44SCGG7AZZ","created_at":"2026-07-05T10:23:31.321081+00:00"},{"alias_kind":"pith_short_16","alias_value":"MY44SCGG7AZZRZ2M","created_at":"2026-07-05T10:23:31.321081+00:00"},{"alias_kind":"pith_short_8","alias_value":"MY44SCGG","created_at":"2026-07-05T10:23:31.321081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25246","citing_title":"Multilingual Hematology Visual Question Answering Dataset","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11106","citing_title":"FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10286","citing_title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10286","citing_title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08815","citing_title":"Towards Responsible Multimodal Medical Reasoning via Context-Aligned Vision-Language Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK","json":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK.json","graph_json":"https://pith.science/api/pith-number/MY44SCGG7AZZRZ2MR4CSCIJNZK/graph.json","events_json":"https://pith.science/api/pith-number/MY44SCGG7AZZRZ2MR4CSCIJNZK/events.json","paper":"https://pith.science/paper/MY44SCGG"},"agent_actions":{"view_html":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK","download_json":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK.json","view_paper":"https://pith.science/paper/MY44SCGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01863&json=true","fetch_graph":"https://pith.science/api/pith-number/MY44SCGG7AZZRZ2MR4CSCIJNZK/graph.json","fetch_events":"https://pith.science/api/pith-number/MY44SCGG7AZZRZ2MR4CSCIJNZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK/action/storage_attestation","attest_author":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK/action/author_attestation","sign_citation":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK/action/citation_signature","submit_replication":"https://pith.science/pith/MY44SCGG7AZZRZ2MR4CSCIJNZK/action/replication_record"}},"created_at":"2026-07-05T10:23:31.321081+00:00","updated_at":"2026-07-05T10:23:31.321081+00:00"}