{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6JILF7CL6AAK5ME7WKRDYM4XZE","short_pith_number":"pith:6JILF7CL","schema_version":"1.0","canonical_sha256":"f250b2fc4bf000aeb09fb2a23c3397c92a3e23f0988a30dd64b1ace06271bccf","source":{"kind":"arxiv","id":"2604.11197","version":2},"attestation_state":"computed","paper":{"title":"MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Yao, Hongchun Lu, Jiahui Peng, Jingwen Li, Jin Ye, Junlong Cheng, Lincheng Jiang, Min Zhu, Sibo Ju, Xue Li, Yanzhou Su, Yujie Lu","submitted_at":"2026-04-13T08:53:36Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates m"},"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":"2604.11197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T08:53:36Z","cross_cats_sorted":[],"title_canon_sha256":"c9d5ec85785d74f94ed33ab8ff14c1ed72ed7dbc7e1704fa2de0710b347d8cfa","abstract_canon_sha256":"8cee334b89f2404f5d583791ee94868b81342b856d1b8a00ac8cfa1f7185add9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:27.719595Z","signature_b64":"Iqdh/5lHtKsrEpVycSVTA8uWPEPvj3AwA1H1YFw1aVSak9/CSiR90G1iBRwTnVuJIQUuiTL38Ls+Y+t2YtdrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f250b2fc4bf000aeb09fb2a23c3397c92a3e23f0988a30dd64b1ace06271bccf","last_reissued_at":"2026-06-24T01:14:27.719182Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:27.719182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Yao, Hongchun Lu, Jiahui Peng, Jingwen Li, Jin Ye, Junlong Cheng, Lincheng Jiang, Min Zhu, Sibo Ju, Xue Li, Yanzhou Su, Yujie Lu","submitted_at":"2026-04-13T08:53:36Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates m"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The feature-level region prompt integration mechanism enables it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MedP-CLIP is a medical CLIP variant with feature-level region prompt integration, pre-trained on 6.4 million images and 97.3 million region annotations, that outperforms baselines in zero-shot recognition and interactive segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"11e7bc0b627b878b90658b9776078cd8433840f9c0d7f524d724f069859b717b"},"source":{"id":"2604.11197","kind":"arxiv","version":2},"verdict":{"id":"b92f995b-b78c-48a6-b20e-7bd1ffa7798d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:50:56.118485Z","strongest_claim":"MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis.","one_line_summary":"MedP-CLIP is a medical CLIP variant with feature-level region prompt integration, pre-trained on 6.4 million images and 97.3 million region annotations, that outperforms baselines in zero-shot recognition and interactive segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The feature-level region prompt integration mechanism enables it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions.","pith_extraction_headline":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11197/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":"2604.11197","created_at":"2026-06-24T01:14:27.719238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.11197v2","created_at":"2026-06-24T01:14:27.719238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11197","created_at":"2026-06-24T01:14:27.719238+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JILF7CL6AAK","created_at":"2026-06-24T01:14:27.719238+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JILF7CL6AAK5ME7","created_at":"2026-06-24T01:14:27.719238+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JILF7CL","created_at":"2026-06-24T01:14:27.719238+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/6JILF7CL6AAK5ME7WKRDYM4XZE","json":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE.json","graph_json":"https://pith.science/api/pith-number/6JILF7CL6AAK5ME7WKRDYM4XZE/graph.json","events_json":"https://pith.science/api/pith-number/6JILF7CL6AAK5ME7WKRDYM4XZE/events.json","paper":"https://pith.science/paper/6JILF7CL"},"agent_actions":{"view_html":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE","download_json":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE.json","view_paper":"https://pith.science/paper/6JILF7CL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.11197&json=true","fetch_graph":"https://pith.science/api/pith-number/6JILF7CL6AAK5ME7WKRDYM4XZE/graph.json","fetch_events":"https://pith.science/api/pith-number/6JILF7CL6AAK5ME7WKRDYM4XZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/action/storage_attestation","attest_author":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/action/author_attestation","sign_citation":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/action/citation_signature","submit_replication":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/action/replication_record"}},"created_at":"2026-06-24T01:14:27.719238+00:00","updated_at":"2026-06-24T01:14:27.719238+00:00"}