{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:36R3LCX2OEGZM4K7ZOON6R3SAJ","short_pith_number":"pith:36R3LCX2","schema_version":"1.0","canonical_sha256":"dfa3b58afa710d96715fcb9cdf47720240afc26384fbd99d7db69f05797d8255","source":{"kind":"arxiv","id":"2603.27176","version":2},"attestation_state":"computed","paper":{"title":"MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ginny Y. Wong, Jaeik Kim, Jaeyoung Do, Ka Chun Cheung, Namjoon Kim, Pa Hong, Sunghwan Steve Cho, Woohyeon Park, Wookyoung Jeong, Yoojin Nam","submitted_at":"2026-03-28T07:26:40Z","abstract_excerpt":"Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present MEDIC-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (<Ano>) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter image difference tokens (<Diff"},"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":"2603.27176","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-28T07:26:40Z","cross_cats_sorted":[],"title_canon_sha256":"ac5c83f71fac87b312c171d5772d7f2ba923ef514aee6fa46b93f665f91b8b76","abstract_canon_sha256":"c1aa427f95d27a3657e21336fc18c0174ac5e4938e6614f5e211d03a2c9df51c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:24:31.512508Z","signature_b64":"hPmg1pzWKvhSbYzxspjCqzImbvXyNMYorxGvJCiZwvTkNChvyqppkaJmC1U/hUjBN7rmTMQaclB+l9pZs+V5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa3b58afa710d96715fcb9cdf47720240afc26384fbd99d7db69f05797d8255","last_reissued_at":"2026-07-29T01:24:31.511450Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:24:31.511450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ginny Y. Wong, Jaeik Kim, Jaeyoung Do, Ka Chun Cheung, Namjoon Kim, Pa Hong, Sunghwan Steve Cho, Woohyeon Park, Wookyoung Jeong, Yoojin Nam","submitted_at":"2026-03-28T07:26:40Z","abstract_excerpt":"Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present MEDIC-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (<Ano>) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter image difference tokens (<Diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.27176","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/2603.27176/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":"2603.27176","created_at":"2026-07-29T01:24:31.511926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27176v2","created_at":"2026-07-29T01:24:31.511926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27176","created_at":"2026-07-29T01:24:31.511926+00:00"},{"alias_kind":"pith_short_12","alias_value":"36R3LCX2OEGZ","created_at":"2026-07-29T01:24:31.511926+00:00"},{"alias_kind":"pith_short_16","alias_value":"36R3LCX2OEGZM4K7","created_at":"2026-07-29T01:24:31.511926+00:00"},{"alias_kind":"pith_short_8","alias_value":"36R3LCX2","created_at":"2026-07-29T01:24:31.511926+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/36R3LCX2OEGZM4K7ZOON6R3SAJ","json":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ.json","graph_json":"https://pith.science/api/pith-number/36R3LCX2OEGZM4K7ZOON6R3SAJ/graph.json","events_json":"https://pith.science/api/pith-number/36R3LCX2OEGZM4K7ZOON6R3SAJ/events.json","paper":"https://pith.science/paper/36R3LCX2"},"agent_actions":{"view_html":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ","download_json":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ.json","view_paper":"https://pith.science/paper/36R3LCX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27176&json=true","fetch_graph":"https://pith.science/api/pith-number/36R3LCX2OEGZM4K7ZOON6R3SAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/36R3LCX2OEGZM4K7ZOON6R3SAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ/action/storage_attestation","attest_author":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ/action/author_attestation","sign_citation":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ/action/citation_signature","submit_replication":"https://pith.science/pith/36R3LCX2OEGZM4K7ZOON6R3SAJ/action/replication_record"}},"created_at":"2026-07-29T01:24:31.511926+00:00","updated_at":"2026-07-29T01:24:31.511926+00:00"}