{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CKRJNXYKVRGXFCRWTQIIXYO3TL","short_pith_number":"pith:CKRJNXYK","schema_version":"1.0","canonical_sha256":"12a296df0aac4d728a369c108be1db9af7f22d8c79fb2df20419eabc1d5c0547","source":{"kind":"arxiv","id":"2411.12195","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Jian Chen, Johan Verjans, Minh-Son To, Qi Chen, Qi Wu, Ruoshan Zhao, Sinuo Wang, Vu Minh Hieu Phan, Yong Xia, Yutong Xie, Zhibin Liao","submitted_at":"2024-11-19T03:27:05Z","abstract_excerpt":"Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced public health monitoring, disease surveillance, and policy-making through more efficient analysis of large data sets. MVLMS integrate natural language processing with medical images to enable a more comprehensive and contextual understanding of medical "},"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":"2411.12195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-19T03:27:05Z","cross_cats_sorted":[],"title_canon_sha256":"f239cd2a241bc2812c0ab3aa7af141a8ea290492902706a8f7b234ad4c467d53","abstract_canon_sha256":"797dfb720af07485e0cec838363c77da1111e956394839f482b1ff70c1c7788f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:17.485731Z","signature_b64":"vSZXkzAakNRV6Iy2slOfom44f9MTiBFDjZ9BqVA3rzkdFeAlDrUPNCC2neQnctDwSFMoLeXQGLNbtiyV/vmnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12a296df0aac4d728a369c108be1db9af7f22d8c79fb2df20419eabc1d5c0547","last_reissued_at":"2026-07-05T09:37:17.485243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:17.485243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Jian Chen, Johan Verjans, Minh-Son To, Qi Chen, Qi Wu, Ruoshan Zhao, Sinuo Wang, Vu Minh Hieu Phan, Yong Xia, Yutong Xie, Zhibin Liao","submitted_at":"2024-11-19T03:27:05Z","abstract_excerpt":"Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced public health monitoring, disease surveillance, and policy-making through more efficient analysis of large data sets. MVLMS integrate natural language processing with medical images to enable a more comprehensive and contextual understanding of medical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12195","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/2411.12195/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":"2411.12195","created_at":"2026-07-05T09:37:17.485300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12195v1","created_at":"2026-07-05T09:37:17.485300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12195","created_at":"2026-07-05T09:37:17.485300+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKRJNXYKVRGX","created_at":"2026-07-05T09:37:17.485300+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKRJNXYKVRGXFCRW","created_at":"2026-07-05T09:37:17.485300+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKRJNXYK","created_at":"2026-07-05T09:37:17.485300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15997","citing_title":"Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL","json":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL.json","graph_json":"https://pith.science/api/pith-number/CKRJNXYKVRGXFCRWTQIIXYO3TL/graph.json","events_json":"https://pith.science/api/pith-number/CKRJNXYKVRGXFCRWTQIIXYO3TL/events.json","paper":"https://pith.science/paper/CKRJNXYK"},"agent_actions":{"view_html":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL","download_json":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL.json","view_paper":"https://pith.science/paper/CKRJNXYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12195&json=true","fetch_graph":"https://pith.science/api/pith-number/CKRJNXYKVRGXFCRWTQIIXYO3TL/graph.json","fetch_events":"https://pith.science/api/pith-number/CKRJNXYKVRGXFCRWTQIIXYO3TL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL/action/storage_attestation","attest_author":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL/action/author_attestation","sign_citation":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL/action/citation_signature","submit_replication":"https://pith.science/pith/CKRJNXYKVRGXFCRWTQIIXYO3TL/action/replication_record"}},"created_at":"2026-07-05T09:37:17.485300+00:00","updated_at":"2026-07-05T09:37:17.485300+00:00"}