{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WBEAKF5XZGMJHU3EKX4TOACFUE","short_pith_number":"pith:WBEAKF5X","schema_version":"1.0","canonical_sha256":"b0480517b7c99893d36455f9370045a115221afae0c192802aa2fbac680511e8","source":{"kind":"arxiv","id":"2507.22902","version":1},"attestation_state":"computed","paper":{"title":"Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.HC","authors_text":"Adam Z. Oskowitz, Evgeniy Makarov, Hashim Hayat, Maksim Kudrautsau, Matt Pavelle, Piotr Varaksin, Tim Tsykunou, Vlad Melnichenko","submitted_at":"2025-06-27T19:04:44Z","abstract_excerpt":"Background: Globally we face a projected shortage of 11 million healthcare practitioners by 2030, and administrative burden consumes 50% of clinical time. Artificial intelligence (AI) has the potential to help alleviate these problems. However, no end-to-end autonomous large language model (LLM)-based AI system has been rigorously evaluated in real-world clinical practice. In this study, we evaluated whether a multi-agent LLM-based AI framework can function autonomously as an AI doctor in a virtual urgent care setting. Methods: We retrospectively compared the performance of the multi-agent AI "},"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":"2507.22902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-27T19:04:44Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"title_canon_sha256":"6b66632a7a3fd086c6e79f41a3cb8089aa78556e8caa0ad6d4b898625e8ca775","abstract_canon_sha256":"bc1712cd423df39c1d28531e85140e48b0694450cd587a192f1fb837daf11f23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:01.170357Z","signature_b64":"xp7eL4skh4Mxs/P0YcjY0dWvlzXoqyXTq47mgKFLY0oaN44zrMvG+kN1CRIjTab9aM7lGdeQl4hiCAxXd7cLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0480517b7c99893d36455f9370045a115221afae0c192802aa2fbac680511e8","last_reissued_at":"2026-07-05T11:46:01.169792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:01.169792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.HC","authors_text":"Adam Z. Oskowitz, Evgeniy Makarov, Hashim Hayat, Maksim Kudrautsau, Matt Pavelle, Piotr Varaksin, Tim Tsykunou, Vlad Melnichenko","submitted_at":"2025-06-27T19:04:44Z","abstract_excerpt":"Background: Globally we face a projected shortage of 11 million healthcare practitioners by 2030, and administrative burden consumes 50% of clinical time. Artificial intelligence (AI) has the potential to help alleviate these problems. However, no end-to-end autonomous large language model (LLM)-based AI system has been rigorously evaluated in real-world clinical practice. In this study, we evaluated whether a multi-agent LLM-based AI framework can function autonomously as an AI doctor in a virtual urgent care setting. Methods: We retrospectively compared the performance of the multi-agent AI "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22902","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/2507.22902/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":"2507.22902","created_at":"2026-07-05T11:46:01.169852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22902v1","created_at":"2026-07-05T11:46:01.169852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22902","created_at":"2026-07-05T11:46:01.169852+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBEAKF5XZGMJ","created_at":"2026-07-05T11:46:01.169852+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBEAKF5XZGMJHU3E","created_at":"2026-07-05T11:46:01.169852+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBEAKF5X","created_at":"2026-07-05T11:46:01.169852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04012","citing_title":"SymptomAI: Toward a Conversational AI Agent for Everyday Symptom Assessment","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04012","citing_title":"SymptomAI: Toward a Conversational AI Agent for Everyday Symptom Assessment","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE","json":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE.json","graph_json":"https://pith.science/api/pith-number/WBEAKF5XZGMJHU3EKX4TOACFUE/graph.json","events_json":"https://pith.science/api/pith-number/WBEAKF5XZGMJHU3EKX4TOACFUE/events.json","paper":"https://pith.science/paper/WBEAKF5X"},"agent_actions":{"view_html":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE","download_json":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE.json","view_paper":"https://pith.science/paper/WBEAKF5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22902&json=true","fetch_graph":"https://pith.science/api/pith-number/WBEAKF5XZGMJHU3EKX4TOACFUE/graph.json","fetch_events":"https://pith.science/api/pith-number/WBEAKF5XZGMJHU3EKX4TOACFUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE/action/storage_attestation","attest_author":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE/action/author_attestation","sign_citation":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE/action/citation_signature","submit_replication":"https://pith.science/pith/WBEAKF5XZGMJHU3EKX4TOACFUE/action/replication_record"}},"created_at":"2026-07-05T11:46:01.169852+00:00","updated_at":"2026-07-05T11:46:01.169852+00:00"}