{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WUUI4HEPFDUBTCQL4JFNOH3RZA","short_pith_number":"pith:WUUI4HEP","schema_version":"1.0","canonical_sha256":"b5288e1c8f28e8198a0be24ad71f71c827d964fa6939d45dc5faefb5216d2133","source":{"kind":"arxiv","id":"2412.10372","version":1},"attestation_state":"computed","paper":{"title":"UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Muhammad Uzair Khattak, Muzammal Naseer, Salman Khan, Shahina Kunhimon","submitted_at":"2024-12-13T18:59:40Z","abstract_excerpt":"Vision-Language Models (VLMs) trained via contrastive learning have achieved notable success in natural image tasks. However, their application in the medical domain remains limited due to the scarcity of openly accessible, large-scale medical image-text datasets. Existing medical VLMs either train on closed-source proprietary or relatively small open-source datasets that do not generalize well. Similarly, most models remain specific to a single or limited number of medical imaging domains, again restricting their applicability to other modalities. To address this gap, we introduce UniMed, a l"},"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":"2412.10372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"37460aa6732300652a71f8e67aa8638d4a63be47e6e9c4b0bf931d3a96a1b6f6","abstract_canon_sha256":"dec36b93f8046cdb7eaaa43acf700ffb1d4bdedd9876bb63916567bf29ad012d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:57.101230Z","signature_b64":"pLD1lm8W5EiD+xLHXNBSiyCez+I+yJ+mgfxwKntkrW6KZFozYqlPmN/XI0enx01FFGeXCSW7FBx10pHuTt4dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5288e1c8f28e8198a0be24ad71f71c827d964fa6939d45dc5faefb5216d2133","last_reissued_at":"2026-07-05T09:48:57.100654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:57.100654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Muhammad Uzair Khattak, Muzammal Naseer, Salman Khan, Shahina Kunhimon","submitted_at":"2024-12-13T18:59:40Z","abstract_excerpt":"Vision-Language Models (VLMs) trained via contrastive learning have achieved notable success in natural image tasks. However, their application in the medical domain remains limited due to the scarcity of openly accessible, large-scale medical image-text datasets. Existing medical VLMs either train on closed-source proprietary or relatively small open-source datasets that do not generalize well. Similarly, most models remain specific to a single or limited number of medical imaging domains, again restricting their applicability to other modalities. To address this gap, we introduce UniMed, a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10372","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/2412.10372/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":"2412.10372","created_at":"2026-07-05T09:48:57.100715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10372v1","created_at":"2026-07-05T09:48:57.100715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10372","created_at":"2026-07-05T09:48:57.100715+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUUI4HEPFDUB","created_at":"2026-07-05T09:48:57.100715+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUUI4HEPFDUBTCQL","created_at":"2026-07-05T09:48:57.100715+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUUI4HEP","created_at":"2026-07-05T09:48:57.100715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20913","citing_title":"PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08126","citing_title":"One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06760","citing_title":"MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28329","citing_title":"$M^3 QuestionIng$: Multi-modal Multi-span Medical Question Answering","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29586","citing_title":"SonoCLIP: Mask-Guided Region-Aware Vision-Language Pretraining for Fetal Ultrasound Analysis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25944","citing_title":"EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15561","citing_title":"RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08849","citing_title":"Adapting Vision-Language Foundation Model for Next Generation Medical Ultrasound Image Analysis","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05421","citing_title":"DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18545","citing_title":"CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08261","citing_title":"DBMF: A Dual-Branch Multimodal Framework for Out-of-Distribution Detection","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08936","citing_title":"M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA","json":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA.json","graph_json":"https://pith.science/api/pith-number/WUUI4HEPFDUBTCQL4JFNOH3RZA/graph.json","events_json":"https://pith.science/api/pith-number/WUUI4HEPFDUBTCQL4JFNOH3RZA/events.json","paper":"https://pith.science/paper/WUUI4HEP"},"agent_actions":{"view_html":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA","download_json":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA.json","view_paper":"https://pith.science/paper/WUUI4HEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10372&json=true","fetch_graph":"https://pith.science/api/pith-number/WUUI4HEPFDUBTCQL4JFNOH3RZA/graph.json","fetch_events":"https://pith.science/api/pith-number/WUUI4HEPFDUBTCQL4JFNOH3RZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA/action/storage_attestation","attest_author":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA/action/author_attestation","sign_citation":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA/action/citation_signature","submit_replication":"https://pith.science/pith/WUUI4HEPFDUBTCQL4JFNOH3RZA/action/replication_record"}},"created_at":"2026-07-05T09:48:57.100715+00:00","updated_at":"2026-07-05T09:48:57.100715+00:00"}