{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:44VWGUO6VAOQNY2XXKS4XBABMF","short_pith_number":"pith:44VWGUO6","canonical_record":{"source":{"id":"2407.08662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T16:51:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79c2f566f912c0212651aa9554688dcd05db5c64f8b50f6abc7da6d732cc4c6a","abstract_canon_sha256":"5c8d3b279799a08a59c16e5151d4d5242438a75b8d40d7b610e597178865c7c5"},"schema_version":"1.0"},"canonical_sha256":"e72b6351dea81d06e357baa5cb8401615672c198d9e4d282fbbec3ad0d689f3b","source":{"kind":"arxiv","id":"2407.08662","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08662","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08662v1","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08662","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"44VWGUO6VAOQ","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"44VWGUO6VAOQNY2X","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"44VWGUO6","created_at":"2026-07-05T08:42:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:44VWGUO6VAOQNY2XXKS4XBABMF","target":"record","payload":{"canonical_record":{"source":{"id":"2407.08662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T16:51:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79c2f566f912c0212651aa9554688dcd05db5c64f8b50f6abc7da6d732cc4c6a","abstract_canon_sha256":"5c8d3b279799a08a59c16e5151d4d5242438a75b8d40d7b610e597178865c7c5"},"schema_version":"1.0"},"canonical_sha256":"e72b6351dea81d06e357baa5cb8401615672c198d9e4d282fbbec3ad0d689f3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:51.279885Z","signature_b64":"i82hM2EuJ5P0LnSGnlcAGUNERTxdNlo+ifLlFcQ/j5+hd0K/ZaAxyGvq0YBzKI0DtUQYDDE9hof56aI7G+QvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72b6351dea81d06e357baa5cb8401615672c198d9e4d282fbbec3ad0d689f3b","last_reissued_at":"2026-07-05T08:42:51.279498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:51.279498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.08662","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dl0d3kAHDzxploWrLQNUWB0gPMUExdBuOou62UJz55DBcLEM0GfVOKpKws7pRmv6wyEs/Z4LdAw+KBUJd7KBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:27:07.761445Z"},"content_sha256":"be7bb30e16a977a447bc59b975de7982ab3d5a6eb827184ca2ca5f7157863b27","schema_version":"1.0","event_id":"sha256:be7bb30e16a977a447bc59b975de7982ab3d5a6eb827184ca2ca5f7157863b27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:44VWGUO6VAOQNY2XXKS4XBABMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty Estimation of Large Language Models in Medical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hong-Yu Zhou, Jiaxin Wu, Yizhou Yu","submitted_at":"2024-07-11T16:51:33Z","abstract_excerpt":"Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. Deploying LLMs for medical question answering necessitates reliable uncertainty estimation (UE) methods to detect hallucinations. In this work, we benchmark popular UE methods with different model sizes on medical question-answering datasets. Our results show that current approaches generally perform poorly in this domain, highlighting the challenge of UE for medical applications. We also observe that larger models tend to yield better results, sugges"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08662","kind":"arxiv","version":1},"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/2407.08662/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":"2026-07-05T08:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aK5jZ9eNgui3zRgn3Oo/fGrG3T3Og+9CasLQT2DZ9MfffLblHo7D1nZPi+SeDgf6NDBf3YDLDhnHtYmsQW8+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:27:07.761800Z"},"content_sha256":"9d7a9c5db7740023865a5d8d421f4a131ed789f9b92675a95115a2f2c9fca617","schema_version":"1.0","event_id":"sha256:9d7a9c5db7740023865a5d8d421f4a131ed789f9b92675a95115a2f2c9fca617"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/44VWGUO6VAOQNY2XXKS4XBABMF/bundle.json","state_url":"https://pith.science/pith/44VWGUO6VAOQNY2XXKS4XBABMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/44VWGUO6VAOQNY2XXKS4XBABMF/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":"2026-08-23T17:27:07Z","links":{"resolver":"https://pith.science/pith/44VWGUO6VAOQNY2XXKS4XBABMF","bundle":"https://pith.science/pith/44VWGUO6VAOQNY2XXKS4XBABMF/bundle.json","state":"https://pith.science/pith/44VWGUO6VAOQNY2XXKS4XBABMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/44VWGUO6VAOQNY2XXKS4XBABMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:44VWGUO6VAOQNY2XXKS4XBABMF","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":"5c8d3b279799a08a59c16e5151d4d5242438a75b8d40d7b610e597178865c7c5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T16:51:33Z","title_canon_sha256":"79c2f566f912c0212651aa9554688dcd05db5c64f8b50f6abc7da6d732cc4c6a"},"schema_version":"1.0","source":{"id":"2407.08662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08662","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08662v1","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08662","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"44VWGUO6VAOQ","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"44VWGUO6VAOQNY2X","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"44VWGUO6","created_at":"2026-07-05T08:42:51Z"}],"graph_snapshots":[{"event_id":"sha256:9d7a9c5db7740023865a5d8d421f4a131ed789f9b92675a95115a2f2c9fca617","target":"graph","created_at":"2026-07-05T08:42:51Z","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/2407.08662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. Deploying LLMs for medical question answering necessitates reliable uncertainty estimation (UE) methods to detect hallucinations. In this work, we benchmark popular UE methods with different model sizes on medical question-answering datasets. Our results show that current approaches generally perform poorly in this domain, highlighting the challenge of UE for medical applications. We also observe that larger models tend to yield better results, sugges","authors_text":"Hong-Yu Zhou, Jiaxin Wu, Yizhou Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T16:51:33Z","title":"Uncertainty Estimation of Large Language Models in Medical Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08662","kind":"arxiv","version":1},"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:be7bb30e16a977a447bc59b975de7982ab3d5a6eb827184ca2ca5f7157863b27","target":"record","created_at":"2026-07-05T08:42:51Z","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":"5c8d3b279799a08a59c16e5151d4d5242438a75b8d40d7b610e597178865c7c5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T16:51:33Z","title_canon_sha256":"79c2f566f912c0212651aa9554688dcd05db5c64f8b50f6abc7da6d732cc4c6a"},"schema_version":"1.0","source":{"id":"2407.08662","kind":"arxiv","version":1}},"canonical_sha256":"e72b6351dea81d06e357baa5cb8401615672c198d9e4d282fbbec3ad0d689f3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e72b6351dea81d06e357baa5cb8401615672c198d9e4d282fbbec3ad0d689f3b","first_computed_at":"2026-07-05T08:42:51.279498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:51.279498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i82hM2EuJ5P0LnSGnlcAGUNERTxdNlo+ifLlFcQ/j5+hd0K/ZaAxyGvq0YBzKI0DtUQYDDE9hof56aI7G+QvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:51.279885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be7bb30e16a977a447bc59b975de7982ab3d5a6eb827184ca2ca5f7157863b27","sha256:9d7a9c5db7740023865a5d8d421f4a131ed789f9b92675a95115a2f2c9fca617"],"state_sha256":"d17aa5025da254fa13e741a9d38d2223c4f5bfd2b710944d3e804f9ea4e1a23b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8/y7Nd8F5EwmYtl5lXKB9HDrRMfz36HWuZe5Q/Emb6FyKA0nnFVd8j+sQb85Upj0a9ruf5f4jXmOdqStm/sQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:27:07.765355Z","bundle_sha256":"0623c1b47f9e5ebf4187330a2f6b85e5887879f34ba89d3bec45c75ba537e15d"}}