{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RCCX2BSEQQGPTZREIKKBCAWFTK","short_pith_number":"pith:RCCX2BSE","schema_version":"1.0","canonical_sha256":"88857d0644840cf9e62442941102c59a8f4926f4cbc359e74d2d94cd37434da9","source":{"kind":"arxiv","id":"2310.20381","version":5},"attestation_state":"computed","paper":{"title":"A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lei Wang, Leyang Cui, Lingqiao Liu, Longyue Wang, Luping Zhou, Xinyu Liang, Yingshu Li, Yunyi Liu, Zhanyu Wang, Zhaopeng Tu","submitted_at":"2023-10-31T11:39:09Z","abstract_excerpt":"This work conducts an evaluation of GPT-4V's multimodal capability for medical image analysis, with a focus on three representative tasks of radiology report generation, medical visual question answering, and medical visual grounding. For the evaluation, a set of prompts is designed for each task to induce the corresponding capability of GPT-4V to produce sufficiently good outputs. Three evaluation ways including quantitative analysis, human evaluation, and case study are employed to achieve an in-depth and extensive evaluation. Our evaluation shows that GPT-4V excels in understanding 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":"2310.20381","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T11:39:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fef37edc4a4da799e0be74a481bf5d69aa3389965e72389fefd7e7bb3520eb01","abstract_canon_sha256":"8b709de1a05ff31a2be50cea10f41c08728e19c59c857521b7ed9118fc412621"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:31.415532Z","signature_b64":"sYmRJcrmjnHB2YKiclbj/oaPuhWdcKWjUhzM+OZ7Dx0b/Wi/+Aj4KEJt5f+908/AwNpEAf5YiBxBSNY1nuVvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88857d0644840cf9e62442941102c59a8f4926f4cbc359e74d2d94cd37434da9","last_reissued_at":"2026-07-05T07:39:31.415037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:31.415037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lei Wang, Leyang Cui, Lingqiao Liu, Longyue Wang, Luping Zhou, Xinyu Liang, Yingshu Li, Yunyi Liu, Zhanyu Wang, Zhaopeng Tu","submitted_at":"2023-10-31T11:39:09Z","abstract_excerpt":"This work conducts an evaluation of GPT-4V's multimodal capability for medical image analysis, with a focus on three representative tasks of radiology report generation, medical visual question answering, and medical visual grounding. For the evaluation, a set of prompts is designed for each task to induce the corresponding capability of GPT-4V to produce sufficiently good outputs. Three evaluation ways including quantitative analysis, human evaluation, and case study are employed to achieve an in-depth and extensive evaluation. Our evaluation shows that GPT-4V excels in understanding medical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20381","kind":"arxiv","version":5},"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/2310.20381/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":"2310.20381","created_at":"2026-07-05T07:39:31.415094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20381v5","created_at":"2026-07-05T07:39:31.415094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20381","created_at":"2026-07-05T07:39:31.415094+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCCX2BSEQQGP","created_at":"2026-07-05T07:39:31.415094+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCCX2BSEQQGPTZRE","created_at":"2026-07-05T07:39:31.415094+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCCX2BSE","created_at":"2026-07-05T07:39:31.415094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07109","citing_title":"The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK","json":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK.json","graph_json":"https://pith.science/api/pith-number/RCCX2BSEQQGPTZREIKKBCAWFTK/graph.json","events_json":"https://pith.science/api/pith-number/RCCX2BSEQQGPTZREIKKBCAWFTK/events.json","paper":"https://pith.science/paper/RCCX2BSE"},"agent_actions":{"view_html":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK","download_json":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK.json","view_paper":"https://pith.science/paper/RCCX2BSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20381&json=true","fetch_graph":"https://pith.science/api/pith-number/RCCX2BSEQQGPTZREIKKBCAWFTK/graph.json","fetch_events":"https://pith.science/api/pith-number/RCCX2BSEQQGPTZREIKKBCAWFTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK/action/storage_attestation","attest_author":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK/action/author_attestation","sign_citation":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK/action/citation_signature","submit_replication":"https://pith.science/pith/RCCX2BSEQQGPTZREIKKBCAWFTK/action/replication_record"}},"created_at":"2026-07-05T07:39:31.415094+00:00","updated_at":"2026-07-05T07:39:31.415094+00:00"}