{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CXCY7WHFPIS7QQEVT7ZI3L2X2P","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":"755c7a5f51f93e01167ee4882eabd56ed92555d4920bd305959fbc8984bf3f07","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T15:51:06Z","title_canon_sha256":"7fcaa275ebbb8fd47406a41393308de969763ac109c97f44882b257f308abbee"},"schema_version":"1.0","source":{"id":"2405.00716","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00716","created_at":"2026-07-05T09:21:04Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00716v4","created_at":"2026-07-05T09:21:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00716","created_at":"2026-07-05T09:21:04Z"},{"alias_kind":"pith_short_12","alias_value":"CXCY7WHFPIS7","created_at":"2026-07-05T09:21:04Z"},{"alias_kind":"pith_short_16","alias_value":"CXCY7WHFPIS7QQEV","created_at":"2026-07-05T09:21:04Z"},{"alias_kind":"pith_short_8","alias_value":"CXCY7WHF","created_at":"2026-07-05T09:21:04Z"}],"graph_snapshots":[{"event_id":"sha256:0c6d18bd61bea10e8ab2f5b9bea906035a3f34006f20c4dee9a0a6da8db59664","target":"graph","created_at":"2026-07-05T09:21:04Z","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/2405.00716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical decisions involve answering open-ended questions without pre-set options. To better understand LLMs in the clinic, we construct a benchmark ClinicBench. We first collect eleven existing datasets covering diverse clinical language generation, understanding, and reasoning tasks. Furthermore, we construct six novel datasets and clinical tasks that are complex but com","authors_text":"Anshul Thakur, Bing Yin, Chen Luo, David A. Clifton, Fenglin Liu, Haoming Jiang, Hongjian Zhou, Jingfeng Yang, Lei Clifton, Ming Zeng, Omid Rohanian, Priyanka Nigam, Qingyu Yin, Sreyashi Nag, Xianfeng Tang, Xuan Zhou, Yifan Gao, Yining Hua, Zheng Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T15:51:06Z","title":"Large Language Models in the Clinic: A Comprehensive Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00716","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":"sha256:0c9b1e31b2ce6d6f5e7ec7fad15bb1feac66c39373370ad3593811246640ed48","target":"record","created_at":"2026-07-05T09:21:04Z","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":"755c7a5f51f93e01167ee4882eabd56ed92555d4920bd305959fbc8984bf3f07","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T15:51:06Z","title_canon_sha256":"7fcaa275ebbb8fd47406a41393308de969763ac109c97f44882b257f308abbee"},"schema_version":"1.0","source":{"id":"2405.00716","kind":"arxiv","version":4}},"canonical_sha256":"15c58fd8e57a25f840959ff28daf57d3d428d903b680495d195e9d973cf23a4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15c58fd8e57a25f840959ff28daf57d3d428d903b680495d195e9d973cf23a4e","first_computed_at":"2026-07-05T09:21:04.097705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:04.097705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ho2FpQaudhWS/gTQJUm8lEkfOxxkkJM0Pr/J6apLPCNJgqpNxmZ4c6EogMLjxv8yaCOEm5lmfqzWD01sm4lXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:04.098227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00716","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c9b1e31b2ce6d6f5e7ec7fad15bb1feac66c39373370ad3593811246640ed48","sha256:0c6d18bd61bea10e8ab2f5b9bea906035a3f34006f20c4dee9a0a6da8db59664"],"state_sha256":"3f37b9f450af476c00361647bf01ca86b4aa1b20d56a5186ddb36dfb6abe6e8c"}