{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6JILF7CL6AAK5ME7WKRDYM4XZE","short_pith_number":"pith:6JILF7CL","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"},"canonical_sha256":"f250b2fc4bf000aeb09fb2a23c3397c92a3e23f0988a30dd64b1ace06271bccf","source":{"kind":"arxiv","id":"2604.11197","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11197","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11197v2","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11197","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"6JILF7CL6AAK","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"6JILF7CL6AAK5ME7","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"6JILF7CL","created_at":"2026-06-24T01:14:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6JILF7CL6AAK5ME7WKRDYM4XZE","target":"record","payload":{"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"},"canonical_sha256":"f250b2fc4bf000aeb09fb2a23c3397c92a3e23f0988a30dd64b1ace06271bccf","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"},"source_kind":"arxiv","source_id":"2604.11197","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kcGLQO+T4pu7Hht05Kj7b9hAyP+rkkz5qb2lxcYAtzl43Jm1fO/Jyxaj2wPe2WEoY58xmmRDIxHmPxetlLWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T10:57:57.060008Z"},"content_sha256":"4b77f45340b4b4ea6d51e0f8d61beb65fb03d565052cf67b93cccb2ae2f410db","schema_version":"1.0","event_id":"sha256:4b77f45340b4b4ea6d51e0f8d61beb65fb03d565052cf67b93cccb2ae2f410db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6JILF7CL6AAK5ME7WKRDYM4XZE","target":"graph","payload":{"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"},"verdict_id":"b92f995b-b78c-48a6-b20e-7bd1ffa7798d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9brkQLfvgdGtod150j6XAUVgeAuxDZQ94EtQ6m6ooiDVbujXnyEoyyKJcfeesRKxt88S9vEzcfPE4IgRjjRzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T10:57:57.060483Z"},"content_sha256":"fcf68345448e1946a235c0fd0f94b0da538099c34b3a00d1cc3420f97bc3f2f4","schema_version":"1.0","event_id":"sha256:fcf68345448e1946a235c0fd0f94b0da538099c34b3a00d1cc3420f97bc3f2f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/bundle.json","state_url":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-03T10:57:57Z","links":{"resolver":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE","bundle":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/bundle.json","state":"https://pith.science/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JILF7CL6AAK5ME7WKRDYM4XZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6JILF7CL6AAK5ME7WKRDYM4XZE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8cee334b89f2404f5d583791ee94868b81342b856d1b8a00ac8cfa1f7185add9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T08:53:36Z","title_canon_sha256":"c9d5ec85785d74f94ed33ab8ff14c1ed72ed7dbc7e1704fa2de0710b347d8cfa"},"schema_version":"1.0","source":{"id":"2604.11197","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11197","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11197v2","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11197","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"6JILF7CL6AAK","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"6JILF7CL6AAK5ME7","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"6JILF7CL","created_at":"2026-06-24T01:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:fcf68345448e1946a235c0fd0f94b0da538099c34b3a00d1cc3420f97bc3f2f4","target":"graph","created_at":"2026-06-24T01:14:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images."}],"snapshot_sha256":"11e7bc0b627b878b90658b9776078cd8433840f9c0d7f524d724f069859b717b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T08:53:36Z","title":"MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11197","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:50:56.118485Z","id":"b92f995b-b78c-48a6-b20e-7bd1ffa7798d","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"MedP-CLIP adds a feature-level region prompt mechanism to CLIP for medical images.","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.","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."}},"verdict_id":"b92f995b-b78c-48a6-b20e-7bd1ffa7798d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b77f45340b4b4ea6d51e0f8d61beb65fb03d565052cf67b93cccb2ae2f410db","target":"record","created_at":"2026-06-24T01:14:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8cee334b89f2404f5d583791ee94868b81342b856d1b8a00ac8cfa1f7185add9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T08:53:36Z","title_canon_sha256":"c9d5ec85785d74f94ed33ab8ff14c1ed72ed7dbc7e1704fa2de0710b347d8cfa"},"schema_version":"1.0","source":{"id":"2604.11197","kind":"arxiv","version":2}},"canonical_sha256":"f250b2fc4bf000aeb09fb2a23c3397c92a3e23f0988a30dd64b1ace06271bccf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f250b2fc4bf000aeb09fb2a23c3397c92a3e23f0988a30dd64b1ace06271bccf","first_computed_at":"2026-06-24T01:14:27.719182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:27.719182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iqdh/5lHtKsrEpVycSVTA8uWPEPvj3AwA1H1YFw1aVSak9/CSiR90G1iBRwTnVuJIQUuiTL38Ls+Y+t2YtdrBQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:27.719595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11197","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b77f45340b4b4ea6d51e0f8d61beb65fb03d565052cf67b93cccb2ae2f410db","sha256:fcf68345448e1946a235c0fd0f94b0da538099c34b3a00d1cc3420f97bc3f2f4"],"state_sha256":"6c5b94680e9f8334a053f60d29ce25d4901d1ac0bbaf3eb1d2c64c6e2f2ffd3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csQ4q6w6bcq1lbdiypQ/y9w436jEit2yMf72aPAkG881fUOzGkSqsHVdSvMBhglaURqcBzB/eRQTh4GQVZ4XCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T10:57:57.062899Z","bundle_sha256":"1fdb1dd96ab606f6fb58f7e813d72845cfe8278f65e691e91fbe5d3d977152cb"}}