{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2PQ5EM6DFKUIQVCHXPZCWALL4I","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":"7a5a3287901d640c460429a91abc9f18fe351648905ee9f245525a6403ab4093","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T13:04:58Z","title_canon_sha256":"9555276c864ac419ac66c4b3f77851071f5500ffbde7834b219b6701f7a9ca07"},"schema_version":"1.0","source":{"id":"2403.08495","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08495","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08495v4","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08495","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"pith_short_12","alias_value":"2PQ5EM6DFKUI","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"pith_short_16","alias_value":"2PQ5EM6DFKUIQVCH","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"pith_short_8","alias_value":"2PQ5EM6D","created_at":"2026-07-05T08:46:22Z"}],"graph_snapshots":[{"event_id":"sha256:416869fe66bbbcd5b9f0d7f3ea8c583d6416dc31e9b618f53391bca46d144afe","target":"graph","created_at":"2026-07-05T08:46:22Z","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/2403.08495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions, yet their application within the medical field remains insufficiently explored. Previous works mainly focus on the performance of medical knowledge with examinations, which is far from the realistic scenarios, falling short in assessing the abilities of LLMs on clinical tasks. In the quest to enhance the application of Large Language Models (LLMs) in healthcare, this paper introduces the Automated Interactive Evaluation (AIE) framework and the State-Aware Patient Simulator (SAPS), targeting the gap bet","authors_text":"Hongcheng Liu, Yanfeng Wang, Yuhao Wang, Yusheng Liao, Yutong Meng, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T13:04:58Z","title":"Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08495","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":"sha256:070ca83e722e46e3928e994323050f389af2742d896e290ecac52c7f3a785da5","target":"record","created_at":"2026-07-05T08:46:22Z","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":"7a5a3287901d640c460429a91abc9f18fe351648905ee9f245525a6403ab4093","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T13:04:58Z","title_canon_sha256":"9555276c864ac419ac66c4b3f77851071f5500ffbde7834b219b6701f7a9ca07"},"schema_version":"1.0","source":{"id":"2403.08495","kind":"arxiv","version":4}},"canonical_sha256":"d3e1d233c32aa8885447bbf22b016be20e8a3fe6e3af396ab13a8bcccc7e5dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3e1d233c32aa8885447bbf22b016be20e8a3fe6e3af396ab13a8bcccc7e5dd9","first_computed_at":"2026-07-05T08:46:22.791803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:22.791803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0Cg2xRYtzsomkFdVlN6C/7IvhuXzHvYSIms+zOseaVAU5tQ8t27PfqUiupXwrI8te8E46xtUxtxdFz9/7KRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:22.792232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08495","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:070ca83e722e46e3928e994323050f389af2742d896e290ecac52c7f3a785da5","sha256:416869fe66bbbcd5b9f0d7f3ea8c583d6416dc31e9b618f53391bca46d144afe"],"state_sha256":"0c94717e0675def2097a7df77b7682a99f169f12eae3e65ce1b913c37b171c41"}