{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ADFOXTIXJB4WENFBXDC36J3UTX","short_pith_number":"pith:ADFOXTIX","schema_version":"1.0","canonical_sha256":"00caebcd1748796234a1b8c5bf27749dc8d6e2a50d1517d73c8d7f8d3774e984","source":{"kind":"arxiv","id":"2312.07353","version":6},"attestation_state":"computed","paper":{"title":"CLIP in Medical Imaging: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinggang Shen, Disheng Liu, Han Wu, Lin Teng, Mei Wang, Qian Wang, Sheng Wang, Yonghao Li, Yuxiao Liu, Zhiming Cui, Zihao Zhao","submitted_at":"2023-12-12T15:21:57Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks due to its generalizability and interpretability. The use of CLIP has recently gained increasing interest in the medical imaging domain, serving as a pre-training paradigm for image-text alignment, or a critical component in diverse clinical tasks. With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP within the"},"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":"2312.07353","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T15:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"d67eb1aab94baeaddd09789f886139ce385f68e84196418893ea70acfcd86b93","abstract_canon_sha256":"54f7ce37ff0266f8c94b3e16a13daed5134b8e5c1572660d4dbd0175acf39146"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:16.366728Z","signature_b64":"zlGCYYRskbHo3GBlSraN5b5kF2WKhZ2sfhfoLuY1zZ9edrqIp+CeNu7jnMYBUNRtYH8NbjPQ+lUy5SZt1phdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00caebcd1748796234a1b8c5bf27749dc8d6e2a50d1517d73c8d7f8d3774e984","last_reissued_at":"2026-07-05T10:39:16.366240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:16.366240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP in Medical Imaging: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinggang Shen, Disheng Liu, Han Wu, Lin Teng, Mei Wang, Qian Wang, Sheng Wang, Yonghao Li, Yuxiao Liu, Zhiming Cui, Zihao Zhao","submitted_at":"2023-12-12T15:21:57Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks due to its generalizability and interpretability. The use of CLIP has recently gained increasing interest in the medical imaging domain, serving as a pre-training paradigm for image-text alignment, or a critical component in diverse clinical tasks. With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP within the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07353","kind":"arxiv","version":6},"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/2312.07353/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":"2312.07353","created_at":"2026-07-05T10:39:16.366301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07353v6","created_at":"2026-07-05T10:39:16.366301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07353","created_at":"2026-07-05T10:39:16.366301+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADFOXTIXJB4W","created_at":"2026-07-05T10:39:16.366301+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADFOXTIXJB4WENFB","created_at":"2026-07-05T10:39:16.366301+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADFOXTIX","created_at":"2026-07-05T10:39:16.366301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25799","citing_title":"Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29776","citing_title":"Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03740","citing_title":"CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18867","citing_title":"Hierarchically Robust Zero-shot Vision-language Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX","json":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX.json","graph_json":"https://pith.science/api/pith-number/ADFOXTIXJB4WENFBXDC36J3UTX/graph.json","events_json":"https://pith.science/api/pith-number/ADFOXTIXJB4WENFBXDC36J3UTX/events.json","paper":"https://pith.science/paper/ADFOXTIX"},"agent_actions":{"view_html":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX","download_json":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX.json","view_paper":"https://pith.science/paper/ADFOXTIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07353&json=true","fetch_graph":"https://pith.science/api/pith-number/ADFOXTIXJB4WENFBXDC36J3UTX/graph.json","fetch_events":"https://pith.science/api/pith-number/ADFOXTIXJB4WENFBXDC36J3UTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX/action/storage_attestation","attest_author":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX/action/author_attestation","sign_citation":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX/action/citation_signature","submit_replication":"https://pith.science/pith/ADFOXTIXJB4WENFBXDC36J3UTX/action/replication_record"}},"created_at":"2026-07-05T10:39:16.366301+00:00","updated_at":"2026-07-05T10:39:16.366301+00:00"}