{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QYLCLNDV755EUV7ZDBGNPJLTUX","short_pith_number":"pith:QYLCLNDV","schema_version":"1.0","canonical_sha256":"861625b475ff7a4a57f9184cd7a573a5e902f7bfd9d08d28ac13c97b112b403d","source":{"kind":"arxiv","id":"2409.00341","version":1},"attestation_state":"computed","paper":{"title":"Aligning Medical Images with General Knowledge from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Hao Chen, Kwang-Ting Cheng, Xiao Fang, Yi Lin","submitted_at":"2024-08-31T03:49:57Z","abstract_excerpt":"Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability. In this work, we propose ViP, a novel visual symptom-guided prompt learning framework for medical image analysis, which facilitates general knowledge transfer from CLIP. ViP consists of two key components: a visual symptom generator (VSG) and a dual-prompt network. Specifically, VSG aims to extract explicable visual symptoms from pre-trained large language models, while the dual-prompt network uti"},"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":"2409.00341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-31T03:49:57Z","cross_cats_sorted":[],"title_canon_sha256":"ce082a2e59fb3e2440cdc3560d50770bd73bc0ff101e1b18cfdac0759ef63fec","abstract_canon_sha256":"c164c28dc720ff187c760fe1204a200b9b58252218224a87d2b4a09670788fc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:45.748656Z","signature_b64":"+31VFjfpH8rxMJd57t04Vd7Ie+hvizeGN4zTxUEveR68yjUO3RIgIuLuUv4/btWLR1S5ujVG7M0T0FcUePyyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"861625b475ff7a4a57f9184cd7a573a5e902f7bfd9d08d28ac13c97b112b403d","last_reissued_at":"2026-07-05T09:01:45.748144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:45.748144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Medical Images with General Knowledge from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Hao Chen, Kwang-Ting Cheng, Xiao Fang, Yi Lin","submitted_at":"2024-08-31T03:49:57Z","abstract_excerpt":"Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability. In this work, we propose ViP, a novel visual symptom-guided prompt learning framework for medical image analysis, which facilitates general knowledge transfer from CLIP. ViP consists of two key components: a visual symptom generator (VSG) and a dual-prompt network. Specifically, VSG aims to extract explicable visual symptoms from pre-trained large language models, while the dual-prompt network uti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00341","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/2409.00341/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":"2409.00341","created_at":"2026-07-05T09:01:45.748204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00341v1","created_at":"2026-07-05T09:01:45.748204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00341","created_at":"2026-07-05T09:01:45.748204+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYLCLNDV755E","created_at":"2026-07-05T09:01:45.748204+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYLCLNDV755EUV7Z","created_at":"2026-07-05T09:01:45.748204+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYLCLNDV","created_at":"2026-07-05T09:01:45.748204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01648","citing_title":"Boosting Ultrasound Image Classification via Attribute-Guided Dual-Branch Framework","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX","json":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX.json","graph_json":"https://pith.science/api/pith-number/QYLCLNDV755EUV7ZDBGNPJLTUX/graph.json","events_json":"https://pith.science/api/pith-number/QYLCLNDV755EUV7ZDBGNPJLTUX/events.json","paper":"https://pith.science/paper/QYLCLNDV"},"agent_actions":{"view_html":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX","download_json":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX.json","view_paper":"https://pith.science/paper/QYLCLNDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00341&json=true","fetch_graph":"https://pith.science/api/pith-number/QYLCLNDV755EUV7ZDBGNPJLTUX/graph.json","fetch_events":"https://pith.science/api/pith-number/QYLCLNDV755EUV7ZDBGNPJLTUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX/action/storage_attestation","attest_author":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX/action/author_attestation","sign_citation":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX/action/citation_signature","submit_replication":"https://pith.science/pith/QYLCLNDV755EUV7ZDBGNPJLTUX/action/replication_record"}},"created_at":"2026-07-05T09:01:45.748204+00:00","updated_at":"2026-07-05T09:01:45.748204+00:00"}