{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YI7DUMWTEV7KRXQLFDWWTQKAHG","short_pith_number":"pith:YI7DUMWT","schema_version":"1.0","canonical_sha256":"c23e3a32d3257ea8de0b28ed69c1403991f288ac96e299fdfd45e94831841cae","source":{"kind":"arxiv","id":"2412.18947","version":4},"attestation_state":"computed","paper":{"title":"MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaiwen Zuo, Yirui Jiang","submitted_at":"2024-12-25T16:51:29Z","abstract_excerpt":"Medical Large Language Models (MLLMs) have demonstrated potential in healthcare applications, yet their propensity for hallucinations -- generating medically implausible or inaccurate information -- presents substantial risks to patient care. This paper introduces MedHallBench, a comprehensive benchmark framework for evaluating and mitigating hallucinations in MLLMs. Our methodology integrates expert-validated medical case scenarios with established medical databases to create a robust evaluation dataset. The framework employs a sophisticated measurement system that combines automated ACHMI (A"},"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":"2412.18947","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T16:51:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ce81ece124cb942704260d3fc6f983a5158ab2159fa0a26c09b708211b7727c","abstract_canon_sha256":"55595baad8b0417fcd26ecf2bbd5c992424d1c6fdd4189622e2ea1f8fcaf311b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:19.278867Z","signature_b64":"Opejy2/s1pGa65CtrS3QgY6jaOjD/E5ItSBCtvfhD00bPPYQmg5SAYPw5Yg47EyGg+87PoBusrYRUiJLzMqtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c23e3a32d3257ea8de0b28ed69c1403991f288ac96e299fdfd45e94831841cae","last_reissued_at":"2026-07-05T10:41:19.278383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:19.278383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaiwen Zuo, Yirui Jiang","submitted_at":"2024-12-25T16:51:29Z","abstract_excerpt":"Medical Large Language Models (MLLMs) have demonstrated potential in healthcare applications, yet their propensity for hallucinations -- generating medically implausible or inaccurate information -- presents substantial risks to patient care. This paper introduces MedHallBench, a comprehensive benchmark framework for evaluating and mitigating hallucinations in MLLMs. Our methodology integrates expert-validated medical case scenarios with established medical databases to create a robust evaluation dataset. The framework employs a sophisticated measurement system that combines automated ACHMI (A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18947","kind":"arxiv","version":4},"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/2412.18947/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":"2412.18947","created_at":"2026-07-05T10:41:19.278439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18947v4","created_at":"2026-07-05T10:41:19.278439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18947","created_at":"2026-07-05T10:41:19.278439+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI7DUMWTEV7K","created_at":"2026-07-05T10:41:19.278439+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI7DUMWTEV7KRXQL","created_at":"2026-07-05T10:41:19.278439+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI7DUMWT","created_at":"2026-07-05T10:41:19.278439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13211","citing_title":"Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17028","citing_title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG","json":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG.json","graph_json":"https://pith.science/api/pith-number/YI7DUMWTEV7KRXQLFDWWTQKAHG/graph.json","events_json":"https://pith.science/api/pith-number/YI7DUMWTEV7KRXQLFDWWTQKAHG/events.json","paper":"https://pith.science/paper/YI7DUMWT"},"agent_actions":{"view_html":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG","download_json":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG.json","view_paper":"https://pith.science/paper/YI7DUMWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18947&json=true","fetch_graph":"https://pith.science/api/pith-number/YI7DUMWTEV7KRXQLFDWWTQKAHG/graph.json","fetch_events":"https://pith.science/api/pith-number/YI7DUMWTEV7KRXQLFDWWTQKAHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/action/storage_attestation","attest_author":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/action/author_attestation","sign_citation":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/action/citation_signature","submit_replication":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/action/replication_record"}},"created_at":"2026-07-05T10:41:19.278439+00:00","updated_at":"2026-07-05T10:41:19.278439+00:00"}