{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YI7DUMWTEV7KRXQLFDWWTQKAHG","short_pith_number":"pith:YI7DUMWT","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"},"canonical_sha256":"c23e3a32d3257ea8de0b28ed69c1403991f288ac96e299fdfd45e94831841cae","source":{"kind":"arxiv","id":"2412.18947","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18947","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18947v4","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18947","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"YI7DUMWTEV7K","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"YI7DUMWTEV7KRXQL","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"YI7DUMWT","created_at":"2026-07-05T10:41:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YI7DUMWTEV7KRXQLFDWWTQKAHG","target":"record","payload":{"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"},"canonical_sha256":"c23e3a32d3257ea8de0b28ed69c1403991f288ac96e299fdfd45e94831841cae","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"},"source_kind":"arxiv","source_id":"2412.18947","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+DdzpZ7E8W8CbTeJWkBmrTw3h+XzkUvx2e/Lm7ug6amK6mOueJGvLbdzuMSIy7ARJcPNyBx2ADaSYU+RPGsNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:01:27.670117Z"},"content_sha256":"34bbb8165d0c39a10e7d7cc9fe7f96beb89e922dd16d5904a65734abde4fedb0","schema_version":"1.0","event_id":"sha256:34bbb8165d0c39a10e7d7cc9fe7f96beb89e922dd16d5904a65734abde4fedb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YI7DUMWTEV7KRXQLFDWWTQKAHG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2l3+agX/E1Ff024I6PPfbLC7dN6uIR9MzRT+e41FscF5sBH4YTsqwcmvIOomwpgRt8Z6G99DkQWJJ1zY7SSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:01:27.670634Z"},"content_sha256":"330eb8ba9f4a8cbf8be8c1a62d5695fc25aa5c5db449b03da2ceb4991f174549","schema_version":"1.0","event_id":"sha256:330eb8ba9f4a8cbf8be8c1a62d5695fc25aa5c5db449b03da2ceb4991f174549"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/bundle.json","state_url":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T03:01:27Z","links":{"resolver":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG","bundle":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/bundle.json","state":"https://pith.science/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YI7DUMWTEV7KRXQLFDWWTQKAHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YI7DUMWTEV7KRXQLFDWWTQKAHG","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":"55595baad8b0417fcd26ecf2bbd5c992424d1c6fdd4189622e2ea1f8fcaf311b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T16:51:29Z","title_canon_sha256":"1ce81ece124cb942704260d3fc6f983a5158ab2159fa0a26c09b708211b7727c"},"schema_version":"1.0","source":{"id":"2412.18947","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18947","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18947v4","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18947","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"YI7DUMWTEV7K","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"YI7DUMWTEV7KRXQL","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"YI7DUMWT","created_at":"2026-07-05T10:41:19Z"}],"graph_snapshots":[{"event_id":"sha256:330eb8ba9f4a8cbf8be8c1a62d5695fc25aa5c5db449b03da2ceb4991f174549","target":"graph","created_at":"2026-07-05T10:41:19Z","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/2412.18947/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kaiwen Zuo, Yirui Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T16:51:29Z","title":"MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18947","kind":"arxiv","version":4},"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":"sha256:34bbb8165d0c39a10e7d7cc9fe7f96beb89e922dd16d5904a65734abde4fedb0","target":"record","created_at":"2026-07-05T10:41:19Z","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":"55595baad8b0417fcd26ecf2bbd5c992424d1c6fdd4189622e2ea1f8fcaf311b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T16:51:29Z","title_canon_sha256":"1ce81ece124cb942704260d3fc6f983a5158ab2159fa0a26c09b708211b7727c"},"schema_version":"1.0","source":{"id":"2412.18947","kind":"arxiv","version":4}},"canonical_sha256":"c23e3a32d3257ea8de0b28ed69c1403991f288ac96e299fdfd45e94831841cae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c23e3a32d3257ea8de0b28ed69c1403991f288ac96e299fdfd45e94831841cae","first_computed_at":"2026-07-05T10:41:19.278383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:19.278383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Opejy2/s1pGa65CtrS3QgY6jaOjD/E5ItSBCtvfhD00bPPYQmg5SAYPw5Yg47EyGg+87PoBusrYRUiJLzMqtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:19.278867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18947","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34bbb8165d0c39a10e7d7cc9fe7f96beb89e922dd16d5904a65734abde4fedb0","sha256:330eb8ba9f4a8cbf8be8c1a62d5695fc25aa5c5db449b03da2ceb4991f174549"],"state_sha256":"d4c83071e95b2e04ca3874d3befaeea05f0e888262c4b8eb57bc7649aea42af5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mexasM2nwTJ407WUPPedTUiEU5odzXr3XVnMNAFWxgqWNssErztBWOhXLiL2hucpCXS+DS0vW+Zj658cD6DPBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:01:27.675077Z","bundle_sha256":"50923f82cc5b212a19eab9be0044f29ee0afe5f8c9282c7d60241c1fb502026d"}}