{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_a3859fe6444d32b5dc02a9df9200165c10e0371ea0a7ba4842de80ac7d554cdf","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_a3859fe6444d32b5dc02a9df9200165c10e0371ea0a7ba4842de80ac7d554cdf","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"242a3d76210304c8e118670ae15e6ae81b600ebf71a5bfb5e477b14d5666216d","published":"Tue, 30 Jun 2026 00:00:00 -0400","receipt_hash":"242a3d76210304c8e118670ae15e6ae81b600ebf71a5bfb5e477b14d5666216d","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"242a3d76210304c8e118670ae15e6ae81b600ebf71a5bfb5e477b14d5666216d","observed_at":"2026-06-30T04:43:04.087680Z","parent_run_hash":"74f7ab392cc702044101fe24a76a2fdad11164cd79ce725aad6c446a477e89c5","published":"Tue, 30 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.28960v1 Announce Type: new \nAbstract: 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 specialized clinical tool (OE), with graders matched to each question's specialty. When comparing answers along five dimensions relevant to clinical decision support -- accuracy, clinical utility, source quality, verifiability, & completeness -- physicians scored the specialized tool highest on all axes; in the primary analysis on Real-POCQi, win difference","title":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","url":"https://arxiv.org/abs/2606.28960","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.28960v1 Announce Type: new \nAbstract: 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 specialized clinical tool (OE), with graders matched to each question's specialty. When comparing answers along five dimensions relevant to clinical decision support -- accuracy, clinical utility, source quality, verifiability, & completeness -- physicians scored the specialized tool highest on all axes; in the primary analysis on Real-POCQi, win difference","title":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-30T04:43:04Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.28960"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:818e0fcc7b38ff91a8f144ae06d4e908836a123fcdc66225680e7ffb982e5b30fba118b2c08e1c0e6cf9fd4e409f6c1f052dd61053c78a58981d745dd151cc0c","signer":"crovia.substrate","subject":{"observed_at":"2026-06-30T04:43:04Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.28960"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"b3f1f8a573bc82ffcec6f11e53188110ed4ef3d0f4808fcd30bc2e723b17be7a","leaf_index":264620,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"3c101cb325f6ea171371d61479d83e1f4b70091467ae20f5c571170c9cd7cd57","side":"right"},{"sibling":"52099697d509b81c60b7276506c8c866439abf33e979c2683f0821ebaf734f62","side":"right"},{"sibling":"93d95ccaadda5cd11656a60dc4e32b4b68f4dca19fb69b09d856bb70d8e68647","side":"left"},{"sibling":"3a0eae65681b48c037f87ec29932569d5578a1538b9502e0cfa510f3e7e77dbb","side":"left"},{"sibling":"1949cff5775dc8378c0adc6cc0302d49c5a8242d7f6464ecdeb96c2ed4fc6b81","side":"right"},{"sibling":"d5a6e24286f5c70bfa5d770b18f58bde2d10bd39fe152e050df615f3d76255b6","side":"left"},{"sibling":"72ca31d723b9813d5bddaf5e89440ca5d3bb8898e526bd86c03fbafd589a70de","side":"right"},{"sibling":"0adb33f90b5325f1bcd6d9d08abc79306f0275cec357b6a5d5a9aeb8dae006eb","side":"left"},{"sibling":"a18aac5bf38684ad71f816483beee037e0b60af41587ea19ba92b263e2076d3e","side":"left"},{"sibling":"e814db3b1e34c91aa2d674ee041f8e093e00869024c9f6f8c4d72cab70c3a87e","side":"right"},{"sibling":"23994bf0974e5c9c7f63a61b4f0a48b0ca756a4adc34a8f85f878e774c37dfbe","side":"right"},{"sibling":"f9b4bed84fa6990c71ad2887c91bda183001f05f6b648f21d1273045a26b11fd","side":"left"},{"sibling":"173d2dc4b29ee04ea41d6d0ebc334c4bc2d46e7ee4230c94765413f24fb4bc42","side":"right"},{"sibling":"112461f7c0ec411116fb5c6c90fe95cea9d8f188b9fe08afe25a837ac02d0071","side":"right"},{"sibling":"ea9488204352c49db8f7daf05eefcd7628ecf9413830346674801a99d0654a94","side":"right"},{"sibling":"6261c13b9922cb657f10d1e5d36ec15d8771cf8766e36c61dcbffb7bed57e396","side":"right"},{"sibling":"fa19aa3faf287618b820bcfceebb366152ad521dd20ef9f51e977816663e448b","side":"right"},{"sibling":"c32f943406b62d1fc59b7f7e243492174c8e1caba8c8a2705f86c773315736e0","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":265374,"merkle_root":"9636001ecab173cb6af10dc7c71eb14585daa62f9c0a6f027046f05633156891","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260630T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-30T05:38:03Z","sig_algorithm":"ed25519","signature":"6d4b8fd9b9da856cbb5fba7540877c6a63fa18a5ec3eaf28dc4d6d1c64921c9c0565f8c95f4b7aec0e7744fd7754844f051baf863db708cad768765b416a7b0c","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_a3859fe6444d32b5dc02a9df9200165c10e0371ea0a7ba4842de80ac7d554cdf"}}