{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRV4GFQO3BSNG7R7ZASS5CJPUX","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":"6dab0129b3cd64aa7f6b361c04cad632a91ccee45f9bb199d24ecc97c73d5a18","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-13T17:38:53Z","title_canon_sha256":"329298b668b7d8094011bd393da2ad3e586fdf5a58433485b44e89dc083faef2"},"schema_version":"1.0","source":{"id":"2405.07960","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07960","created_at":"2026-05-21T13:47:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07960v5","created_at":"2026-05-21T13:47:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07960","created_at":"2026-05-21T13:47:14Z"},{"alias_kind":"pith_short_12","alias_value":"RRV4GFQO3BSN","created_at":"2026-05-21T13:47:14Z"},{"alias_kind":"pith_short_16","alias_value":"RRV4GFQO3BSNG7R7","created_at":"2026-05-21T13:47:14Z"},{"alias_kind":"pith_short_8","alias_value":"RRV4GFQO","created_at":"2026-05-21T13:47:14Z"}],"graph_snapshots":[{"event_id":"sha256:efede858b0b90b7831d28abaa802b1a3b243960b08e4a228db9f79fdb96d6215","target":"graph","created_at":"2026-05-21T13:47:14Z","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/2405.07960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLM) in clinical scenarios is crucial to assessing their potential clinical utility. Existing benchmarks rely heavily on static question-answering, which does not accurately depict the complex, sequential nature of clinical decision-making. Here, we introduce AgentClinic, a multimodal agent benchmark for evaluating LLMs in simulated clinical environments that include patient interactions, multimodal data collection under incomplete information, and the usage of various tools, resulting in an in-depth evaluation across nine medical specialties and seven languag","authors_text":"Carl Harris, Eduardo Reis, Jeffrey Jopling, Michael Moor, Rojin Ziaei, Samuel Schmidgall","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-13T17:38:53Z","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07960","kind":"arxiv","version":5},"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:e4d12ce6135c05cfdffb1d770b40a88214ec2b860dad4c822a2e673cc70cd468","target":"record","created_at":"2026-05-21T13:47:14Z","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":"6dab0129b3cd64aa7f6b361c04cad632a91ccee45f9bb199d24ecc97c73d5a18","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-13T17:38:53Z","title_canon_sha256":"329298b668b7d8094011bd393da2ad3e586fdf5a58433485b44e89dc083faef2"},"schema_version":"1.0","source":{"id":"2405.07960","kind":"arxiv","version":5}},"canonical_sha256":"8c6bc3160ed864d37e3fc8252e892fa5fefc98956feda7b04dfc1e388a6f7a0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c6bc3160ed864d37e3fc8252e892fa5fefc98956feda7b04dfc1e388a6f7a0e","first_computed_at":"2026-05-21T13:47:14.138213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T13:47:14.138213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQf3bBRBTZsz/4Vr4rxTme1qf+PMR+V9DMPuguzUiFFhoYMqzvhhK5bbEGxVpNBjlpsLFCJG2z1GO9FDLmHSBQ==","signature_status":"signed_v1","signed_at":"2026-05-21T13:47:14.140102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07960","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4d12ce6135c05cfdffb1d770b40a88214ec2b860dad4c822a2e673cc70cd468","sha256:efede858b0b90b7831d28abaa802b1a3b243960b08e4a228db9f79fdb96d6215"],"state_sha256":"813f5a05b72a3f83dcaf36aed8544c1711b246b980f47ae714c6f358cf4b2875"}