{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R4DUNTF4OMOF6XWIS5KTUROM7I","short_pith_number":"pith:R4DUNTF4","schema_version":"1.0","canonical_sha256":"8f0746ccbc731c5f5ec897553a45ccfa054e3ed0bda4dfc7303472983631929a","source":{"kind":"arxiv","id":"2402.09742","version":4},"attestation_state":"computed","paper":{"title":"AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Huang, Jialong Tang, Jingren Zhou, Jun Xi, Siyuan Wang, Wei Chen, Zhihao Fan, Zhongyu Wei","submitted_at":"2024-02-15T06:46:48Z","abstract_excerpt":"Artificial intelligence has significantly advanced healthcare, particularly through large language models (LLMs) that excel in medical question answering benchmarks. However, their real-world clinical application remains limited due to the complexities of doctor-patient interactions. To address this, we introduce \\textbf{AI Hospital}, a multi-agent framework simulating dynamic medical interactions between \\emph{Doctor} as player and NPCs including \\emph{Patient}, \\emph{Examiner}, \\emph{Chief Physician}. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the M"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.09742","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T06:46:48Z","cross_cats_sorted":[],"title_canon_sha256":"51c182e4c8e5259e938781448fc1e75df010f45981d38cb0a088fd51e6f4961d","abstract_canon_sha256":"8f709650ccf5e3013963a2232ccbce01a445d8f65cb7298ac69430df509909d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:37.094883Z","signature_b64":"71W2xsZfZbn74FQj8zPeaZU9I4Es3yJ9znLb5yLSNmU/m56IJhb+KX403j9RDD6dLTN4o3BKWTbLg3/LDIQEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f0746ccbc731c5f5ec897553a45ccfa054e3ed0bda4dfc7303472983631929a","last_reissued_at":"2026-07-05T08:37:37.094332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:37.094332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Huang, Jialong Tang, Jingren Zhou, Jun Xi, Siyuan Wang, Wei Chen, Zhihao Fan, Zhongyu Wei","submitted_at":"2024-02-15T06:46:48Z","abstract_excerpt":"Artificial intelligence has significantly advanced healthcare, particularly through large language models (LLMs) that excel in medical question answering benchmarks. However, their real-world clinical application remains limited due to the complexities of doctor-patient interactions. To address this, we introduce \\textbf{AI Hospital}, a multi-agent framework simulating dynamic medical interactions between \\emph{Doctor} as player and NPCs including \\emph{Patient}, \\emph{Examiner}, \\emph{Chief Physician}. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09742","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/2402.09742/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.09742","created_at":"2026-07-05T08:37:37.094414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09742v4","created_at":"2026-07-05T08:37:37.094414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09742","created_at":"2026-07-05T08:37:37.094414+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4DUNTF4OMOF","created_at":"2026-07-05T08:37:37.094414+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4DUNTF4OMOF6XWI","created_at":"2026-07-05T08:37:37.094414+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4DUNTF4","created_at":"2026-07-05T08:37:37.094414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31179","citing_title":"HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19630","citing_title":"Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09788","citing_title":"TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09275","citing_title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01297","citing_title":"RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I","json":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I.json","graph_json":"https://pith.science/api/pith-number/R4DUNTF4OMOF6XWIS5KTUROM7I/graph.json","events_json":"https://pith.science/api/pith-number/R4DUNTF4OMOF6XWIS5KTUROM7I/events.json","paper":"https://pith.science/paper/R4DUNTF4"},"agent_actions":{"view_html":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I","download_json":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I.json","view_paper":"https://pith.science/paper/R4DUNTF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09742&json=true","fetch_graph":"https://pith.science/api/pith-number/R4DUNTF4OMOF6XWIS5KTUROM7I/graph.json","fetch_events":"https://pith.science/api/pith-number/R4DUNTF4OMOF6XWIS5KTUROM7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I/action/storage_attestation","attest_author":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I/action/author_attestation","sign_citation":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I/action/citation_signature","submit_replication":"https://pith.science/pith/R4DUNTF4OMOF6XWIS5KTUROM7I/action/replication_record"}},"created_at":"2026-07-05T08:37:37.094414+00:00","updated_at":"2026-07-05T08:37:37.094414+00:00"}