{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I2WXCCJO6YASQZN2OFH2R6FRUV","short_pith_number":"pith:I2WXCCJO","schema_version":"1.0","canonical_sha256":"46ad71092ef6012865ba714fa8f8b1a576121b278ba018a9f5197d00ff385172","source":{"kind":"arxiv","id":"2606.28960","version":1},"attestation_state":"computed","paper":{"title":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM","stat.AP"],"primary_cat":"cs.AI","authors_text":"Anupam B. Jena, Jean Feng, Jialin Ouyang, Patrick Heagerty, Patrick Vossler, Venkatesh Sivaraman, Vishal Patel, Yifan Mai","submitted_at":"2026-06-27T15:00:20Z","abstract_excerpt":"Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from HealthBench. 149 practicing physicians across 36 states made head-to-head comparisons between answers from three frontier general-purpose models (Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5) and a speciali"},"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":"2606.28960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-27T15:00:20Z","cross_cats_sorted":["q-bio.QM","stat.AP"],"title_canon_sha256":"1286d4162e2b0dcec93e760cccf961eb71f02f62eb6aa6e1fabac1bf62e27949","abstract_canon_sha256":"8992f17336a3c34b1af0265637ac8007b088cd04daba7aa4731738ffa6552a8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:47.278850Z","signature_b64":"2RxZc4Sn9wwGd6Hc69Y5+C/MUDchQ8S5OEATzFiw+0r3cClkyk1Z8RPtBI6OyxvMgKDFR5SOfqXVhWgts4OjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46ad71092ef6012865ba714fa8f8b1a576121b278ba018a9f5197d00ff385172","last_reissued_at":"2026-06-30T01:17:47.277943Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:47.277943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM","stat.AP"],"primary_cat":"cs.AI","authors_text":"Anupam B. Jena, Jean Feng, Jialin Ouyang, Patrick Heagerty, Patrick Vossler, Venkatesh Sivaraman, Vishal Patel, Yifan Mai","submitted_at":"2026-06-27T15:00:20Z","abstract_excerpt":"Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from HealthBench. 149 practicing physicians across 36 states made head-to-head comparisons between answers from three frontier general-purpose models (Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5) and a speciali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28960","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/2606.28960/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":"2606.28960","created_at":"2026-06-30T01:17:47.278023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28960v1","created_at":"2026-06-30T01:17:47.278023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28960","created_at":"2026-06-30T01:17:47.278023+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2WXCCJO6YAS","created_at":"2026-06-30T01:17:47.278023+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2WXCCJO6YASQZN2","created_at":"2026-06-30T01:17:47.278023+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2WXCCJO","created_at":"2026-06-30T01:17:47.278023+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/I2WXCCJO6YASQZN2OFH2R6FRUV","json":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV.json","graph_json":"https://pith.science/api/pith-number/I2WXCCJO6YASQZN2OFH2R6FRUV/graph.json","events_json":"https://pith.science/api/pith-number/I2WXCCJO6YASQZN2OFH2R6FRUV/events.json","paper":"https://pith.science/paper/I2WXCCJO"},"agent_actions":{"view_html":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV","download_json":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV.json","view_paper":"https://pith.science/paper/I2WXCCJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28960&json=true","fetch_graph":"https://pith.science/api/pith-number/I2WXCCJO6YASQZN2OFH2R6FRUV/graph.json","fetch_events":"https://pith.science/api/pith-number/I2WXCCJO6YASQZN2OFH2R6FRUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV/action/storage_attestation","attest_author":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV/action/author_attestation","sign_citation":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV/action/citation_signature","submit_replication":"https://pith.science/pith/I2WXCCJO6YASQZN2OFH2R6FRUV/action/replication_record"}},"created_at":"2026-06-30T01:17:47.278023+00:00","updated_at":"2026-06-30T01:17:47.278023+00:00"}