{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LGY7G5663GUOOQCGDLG4L766GA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eb8c665afec67d36fd169b44534475909229ca94a40f17455f2471473d640d58","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T10:52:17Z","title_canon_sha256":"225a7e187bd7f1988535e48b6ac56b0d8f6a7c5f3e63afa656539f37d456df01"},"schema_version":"1.0","source":{"id":"2401.05827","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05827","created_at":"2026-07-05T08:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05827v2","created_at":"2026-07-05T08:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05827","created_at":"2026-07-05T08:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"LGY7G5663GUO","created_at":"2026-07-05T08:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"LGY7G5663GUOOQCG","created_at":"2026-07-05T08:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"LGY7G566","created_at":"2026-07-05T08:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:e124bbf691a7f779d43c7760a196a7096964caf6b0f1f9c901ce37f99e24fc4d","target":"graph","created_at":"2026-07-05T08:03:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.05827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Honghan Wu, Jinge Wu, Yunsoo Kim","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T10:52:17Z","title":"Hallucination Benchmark in Medical Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05827","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:02cd14b1c86b63449a53f5ba84d46dc19cb3c9671f2dd06cac2916911a72fa43","target":"record","created_at":"2026-07-05T08:03:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eb8c665afec67d36fd169b44534475909229ca94a40f17455f2471473d640d58","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T10:52:17Z","title_canon_sha256":"225a7e187bd7f1988535e48b6ac56b0d8f6a7c5f3e63afa656539f37d456df01"},"schema_version":"1.0","source":{"id":"2401.05827","kind":"arxiv","version":2}},"canonical_sha256":"59b1f377ded9a8e740461acdc5ffde300505b307b4553b1ec6140db1dd4c3bf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b1f377ded9a8e740461acdc5ffde300505b307b4553b1ec6140db1dd4c3bf9","first_computed_at":"2026-07-05T08:03:47.876171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:47.876171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8riBSENgmYvlHCyXiy8vy6XFO7yymf3wFegyiFsyNawMh5OVQzOpq++otJzu6azTW81QBsDQbg4FaSJx9CRZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:47.876652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05827","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02cd14b1c86b63449a53f5ba84d46dc19cb3c9671f2dd06cac2916911a72fa43","sha256:e124bbf691a7f779d43c7760a196a7096964caf6b0f1f9c901ce37f99e24fc4d"],"state_sha256":"0788ab7c8e42db5231366c2d82038cbe74973f06ad95a0b01e8117d404a43972"}