{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V7EWKRYCLUOEUGSDVCZRXCNVKU","short_pith_number":"pith:V7EWKRYC","schema_version":"1.0","canonical_sha256":"afc96547025d1c4a1a43a8b31b89b555197cacfe6d2dfe4124b370a06c4a406e","source":{"kind":"arxiv","id":"2310.19061","version":1},"attestation_state":"computed","paper":{"title":"Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Zhang, Lichao Sun, Lifang He, Rong Zhou, Xiang Li, Zhiling Yan","submitted_at":"2023-10-29T16:26:28Z","abstract_excerpt":"In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i.e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task. Our experiments thoroughly assess GPT-4V's proficiency in answering questions paired with images using both pathology and radiology datasets from 11 modalities (e.g. Microscopy, Dermoscopy, X-ray, CT, etc.) and fifteen objects of interests (brain, liver, lung, etc.). Our datasets encompass a comprehensive range of medical inquiries, including sixteen distinct question types. Throughout our evaluations, we devi"},"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":"2310.19061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-29T16:26:28Z","cross_cats_sorted":[],"title_canon_sha256":"ecff10d69b252835d1efef64a48aacae35ea3167b2589c91b0c0beff30112033","abstract_canon_sha256":"056a2259c606e6d48bff7334a1baa5bf69cb8cabde072de8b88a571f3c15e463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:45.518026Z","signature_b64":"DGSkT9zwF6Kj25oUwUqkmmtAx8CEV3ZtzxdUcJh01xexN0k0fi6xar8QGTJq5dsO8fM/apsgmxz3zYGRBpqQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afc96547025d1c4a1a43a8b31b89b555197cacfe6d2dfe4124b370a06c4a406e","last_reissued_at":"2026-07-05T07:06:45.517518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:45.517518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Zhang, Lichao Sun, Lifang He, Rong Zhou, Xiang Li, Zhiling Yan","submitted_at":"2023-10-29T16:26:28Z","abstract_excerpt":"In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i.e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task. Our experiments thoroughly assess GPT-4V's proficiency in answering questions paired with images using both pathology and radiology datasets from 11 modalities (e.g. Microscopy, Dermoscopy, X-ray, CT, etc.) and fifteen objects of interests (brain, liver, lung, etc.). Our datasets encompass a comprehensive range of medical inquiries, including sixteen distinct question types. Throughout our evaluations, we devi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19061","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/2310.19061/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":"2310.19061","created_at":"2026-07-05T07:06:45.517577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19061v1","created_at":"2026-07-05T07:06:45.517577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19061","created_at":"2026-07-05T07:06:45.517577+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7EWKRYCLUOE","created_at":"2026-07-05T07:06:45.517577+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7EWKRYCLUOEUGSD","created_at":"2026-07-05T07:06:45.517577+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7EWKRYC","created_at":"2026-07-05T07:06:45.517577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05311","citing_title":"Deep Learning for Semen Analysis in Male Infertility: Computer Vision, Multimodal Fusion, and Clinical Translation","ref_index":117,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25546","citing_title":"Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU","json":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU.json","graph_json":"https://pith.science/api/pith-number/V7EWKRYCLUOEUGSDVCZRXCNVKU/graph.json","events_json":"https://pith.science/api/pith-number/V7EWKRYCLUOEUGSDVCZRXCNVKU/events.json","paper":"https://pith.science/paper/V7EWKRYC"},"agent_actions":{"view_html":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU","download_json":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU.json","view_paper":"https://pith.science/paper/V7EWKRYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19061&json=true","fetch_graph":"https://pith.science/api/pith-number/V7EWKRYCLUOEUGSDVCZRXCNVKU/graph.json","fetch_events":"https://pith.science/api/pith-number/V7EWKRYCLUOEUGSDVCZRXCNVKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU/action/storage_attestation","attest_author":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU/action/author_attestation","sign_citation":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU/action/citation_signature","submit_replication":"https://pith.science/pith/V7EWKRYCLUOEUGSDVCZRXCNVKU/action/replication_record"}},"created_at":"2026-07-05T07:06:45.517577+00:00","updated_at":"2026-07-05T07:06:45.517577+00:00"}