{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LGY7G5663GUOOQCGDLG4L766GA","short_pith_number":"pith:LGY7G566","schema_version":"1.0","canonical_sha256":"59b1f377ded9a8e740461acdc5ffde300505b307b4553b1ec6140db1dd4c3bf9","source":{"kind":"arxiv","id":"2401.05827","version":2},"attestation_state":"computed","paper":{"title":"Hallucination Benchmark in Medical Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Honghan Wu, Jinge Wu, Yunsoo Kim","submitted_at":"2024-01-11T10:52:17Z","abstract_excerpt":"The recent success of large language and vision models (LLVMs) on vision question answering (VQA), particularly their applications in medicine (Med-VQA), has shown a great potential of realizing effective visual assistants for healthcare. However, these models are not extensively tested on the hallucination phenomenon in clinical settings. Here, we created a hallucination benchmark of medical images paired with question-answer sets and conducted a comprehensive evaluation of the state-of-the-art models. The study provides an in-depth analysis of current models' limitations and reveals the effe"},"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":"2401.05827","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T10:52:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"225a7e187bd7f1988535e48b6ac56b0d8f6a7c5f3e63afa656539f37d456df01","abstract_canon_sha256":"eb8c665afec67d36fd169b44534475909229ca94a40f17455f2471473d640d58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:47.876652Z","signature_b64":"8riBSENgmYvlHCyXiy8vy6XFO7yymf3wFegyiFsyNawMh5OVQzOpq++otJzu6azTW81QBsDQbg4FaSJx9CRZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b1f377ded9a8e740461acdc5ffde300505b307b4553b1ec6140db1dd4c3bf9","last_reissued_at":"2026-07-05T08:03:47.876171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:47.876171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallucination Benchmark in Medical Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Honghan Wu, Jinge Wu, Yunsoo Kim","submitted_at":"2024-01-11T10:52:17Z","abstract_excerpt":"The recent success of large language and vision models (LLVMs) on vision question answering (VQA), particularly their applications in medicine (Med-VQA), has shown a great potential of realizing effective visual assistants for healthcare. However, these models are not extensively tested on the hallucination phenomenon in clinical settings. Here, we created a hallucination benchmark of medical images paired with question-answer sets and conducted a comprehensive evaluation of the state-of-the-art models. The study provides an in-depth analysis of current models' limitations and reveals the effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05827","kind":"arxiv","version":2},"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/2401.05827/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":"2401.05827","created_at":"2026-07-05T08:03:47.876231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05827v2","created_at":"2026-07-05T08:03:47.876231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05827","created_at":"2026-07-05T08:03:47.876231+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGY7G5663GUO","created_at":"2026-07-05T08:03:47.876231+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGY7G5663GUOOQCG","created_at":"2026-07-05T08:03:47.876231+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGY7G566","created_at":"2026-07-05T08:03:47.876231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.10415","citing_title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09384","citing_title":"LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA","json":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA.json","graph_json":"https://pith.science/api/pith-number/LGY7G5663GUOOQCGDLG4L766GA/graph.json","events_json":"https://pith.science/api/pith-number/LGY7G5663GUOOQCGDLG4L766GA/events.json","paper":"https://pith.science/paper/LGY7G566"},"agent_actions":{"view_html":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA","download_json":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA.json","view_paper":"https://pith.science/paper/LGY7G566","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05827&json=true","fetch_graph":"https://pith.science/api/pith-number/LGY7G5663GUOOQCGDLG4L766GA/graph.json","fetch_events":"https://pith.science/api/pith-number/LGY7G5663GUOOQCGDLG4L766GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA/action/storage_attestation","attest_author":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA/action/author_attestation","sign_citation":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA/action/citation_signature","submit_replication":"https://pith.science/pith/LGY7G5663GUOOQCGDLG4L766GA/action/replication_record"}},"created_at":"2026-07-05T08:03:47.876231+00:00","updated_at":"2026-07-05T08:03:47.876231+00:00"}