{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IDK7UZPI3XEEKXM5P4NHCPNGL5","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":"e273c9f0a3068af7d60fbc48d00e8bb473038bfadee061c74af1fa7aea6529f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T06:17:54Z","title_canon_sha256":"e9a9f4c23133cf8e75ffb9e2b387ef2556330526cc743901a6e437e4f2d80180"},"schema_version":"1.0","source":{"id":"2403.16446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16446","created_at":"2026-07-05T08:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16446v1","created_at":"2026-07-05T08:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16446","created_at":"2026-07-05T08:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"IDK7UZPI3XEE","created_at":"2026-07-05T08:00:16Z"},{"alias_kind":"pith_short_16","alias_value":"IDK7UZPI3XEEKXM5","created_at":"2026-07-05T08:00:16Z"},{"alias_kind":"pith_short_8","alias_value":"IDK7UZPI","created_at":"2026-07-05T08:00:16Z"}],"graph_snapshots":[{"event_id":"sha256:b52880d242f99512b07995e0b825f0d76f063a0d385bd97982f5e25105cbc158","target":"graph","created_at":"2026-07-05T08:00:16Z","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/2403.16446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are gaining increasing interests to improve clinical efficiency for medical diagnosis, owing to their unprecedented performance in modelling natural language. Ensuring the safe and reliable clinical applications, the evaluation of LLMs indeed becomes critical for better mitigating the potential risks, e.g., hallucinations. However, current evaluation methods heavily rely on labor-intensive human participation to achieve human-preferred judgements. To overcome this challenge, we propose an automatic evaluation paradigm tailored to assess the LLMs' capabilities in de","authors_text":"Chenfei Chi, Fangzhou Li, Jinjie Gu, Lei Liu, Liya Ma, Shiwei Lyu Ming Zhang, Wei Xue, Xiangguo Lyu, Xiaowei Ma, Xiaoyan Yang, Yiran Huang, Yue Shen, Zhiqiang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T06:17:54Z","title":"Towards Automatic Evaluation for LLMs' Clinical Capabilities: Metric, Data, and Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16446","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":"sha256:31ef126850100887a63d7a889b84ab0b057bfbcf0b09869a71b6b3c858974d8c","target":"record","created_at":"2026-07-05T08:00:16Z","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":"e273c9f0a3068af7d60fbc48d00e8bb473038bfadee061c74af1fa7aea6529f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T06:17:54Z","title_canon_sha256":"e9a9f4c23133cf8e75ffb9e2b387ef2556330526cc743901a6e437e4f2d80180"},"schema_version":"1.0","source":{"id":"2403.16446","kind":"arxiv","version":1}},"canonical_sha256":"40d5fa65e8ddc8455d9d7f1a713da65f5ce0b97a50b96d0a435b16f6f6b0c1b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40d5fa65e8ddc8455d9d7f1a713da65f5ce0b97a50b96d0a435b16f6f6b0c1b9","first_computed_at":"2026-07-05T08:00:16.118725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:16.118725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A3ivHnfXmEdA0Z3UJM3R39D36uj1tLPNWICjaM2+O9OvjVZf2cn/DzAO0hLYNLSpEwLQNN6NSGOGHD7mja6PAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:16.119157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31ef126850100887a63d7a889b84ab0b057bfbcf0b09869a71b6b3c858974d8c","sha256:b52880d242f99512b07995e0b825f0d76f063a0d385bd97982f5e25105cbc158"],"state_sha256":"8d2ee1520d11fc525eb4f1fd788cbd599bb8d5fe231173eeedbfee10f2a31927"}