{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YORTLV7JP5NEVBTH525DXD2FS6","short_pith_number":"pith:YORTLV7J","schema_version":"1.0","canonical_sha256":"c3a335d7e97f5a4a8667eeba3b8f4597b6f1361562f0dbb18ab151b644b651e8","source":{"kind":"arxiv","id":"2309.10895","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models as Agents in the Clinic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.HC","authors_text":"Ahmed Alaa, Atul J. Butte, Brenda Y. Miao, Eduardo Rodriguez Almaraz, Madhumita Sushil, Nikita Mehandru","submitted_at":"2023-09-19T19:38:28Z","abstract_excerpt":"Recent developments in large language models (LLMs) have unlocked new opportunities for healthcare, from information synthesis to clinical decision support. These new LLMs are not just capable of modeling language, but can also act as intelligent \"agents\" that interact with stakeholders in open-ended conversations and even influence clinical decision-making. Rather than relying on benchmarks that measure a model's ability to process clinical data or answer standardized test questions, LLM agents should be assessed for their performance on real-world clinical tasks. These new evaluation framewo"},"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":"2309.10895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-09-19T19:38:28Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"0fd16aa88324a11fa4a582c8fc2b9c5a8d476fcf68c6ced8ae5c19ed3b483c66","abstract_canon_sha256":"58af181174daa50a21cbb039d2ab5484634c1756fb7fb18def3286d8a0eed05a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:28.171509Z","signature_b64":"JB7rMkkudCecoCq/BHauL973y3jFBVzGrE5k4kXRn0sylKTodf9f7sSkmPL3DMZh3TIUqAj+PZgEqa4fmmZxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3a335d7e97f5a4a8667eeba3b8f4597b6f1361562f0dbb18ab151b644b651e8","last_reissued_at":"2026-07-05T06:52:28.171031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:28.171031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Agents in the Clinic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.HC","authors_text":"Ahmed Alaa, Atul J. Butte, Brenda Y. Miao, Eduardo Rodriguez Almaraz, Madhumita Sushil, Nikita Mehandru","submitted_at":"2023-09-19T19:38:28Z","abstract_excerpt":"Recent developments in large language models (LLMs) have unlocked new opportunities for healthcare, from information synthesis to clinical decision support. These new LLMs are not just capable of modeling language, but can also act as intelligent \"agents\" that interact with stakeholders in open-ended conversations and even influence clinical decision-making. Rather than relying on benchmarks that measure a model's ability to process clinical data or answer standardized test questions, LLM agents should be assessed for their performance on real-world clinical tasks. These new evaluation framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10895","kind":"arxiv","version":1},"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/2309.10895/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":"2309.10895","created_at":"2026-07-05T06:52:28.171084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10895v1","created_at":"2026-07-05T06:52:28.171084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10895","created_at":"2026-07-05T06:52:28.171084+00:00"},{"alias_kind":"pith_short_12","alias_value":"YORTLV7JP5NE","created_at":"2026-07-05T06:52:28.171084+00:00"},{"alias_kind":"pith_short_16","alias_value":"YORTLV7JP5NEVBTH","created_at":"2026-07-05T06:52:28.171084+00:00"},{"alias_kind":"pith_short_8","alias_value":"YORTLV7J","created_at":"2026-07-05T06:52:28.171084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6","json":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6.json","graph_json":"https://pith.science/api/pith-number/YORTLV7JP5NEVBTH525DXD2FS6/graph.json","events_json":"https://pith.science/api/pith-number/YORTLV7JP5NEVBTH525DXD2FS6/events.json","paper":"https://pith.science/paper/YORTLV7J"},"agent_actions":{"view_html":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6","download_json":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6.json","view_paper":"https://pith.science/paper/YORTLV7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10895&json=true","fetch_graph":"https://pith.science/api/pith-number/YORTLV7JP5NEVBTH525DXD2FS6/graph.json","fetch_events":"https://pith.science/api/pith-number/YORTLV7JP5NEVBTH525DXD2FS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6/action/storage_attestation","attest_author":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6/action/author_attestation","sign_citation":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6/action/citation_signature","submit_replication":"https://pith.science/pith/YORTLV7JP5NEVBTH525DXD2FS6/action/replication_record"}},"created_at":"2026-07-05T06:52:28.171084+00:00","updated_at":"2026-07-05T06:52:28.171084+00:00"}