{"_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_f40df86efbf8ad09b21ec4230b3cda7773e0666b47391dcfb1c173ed1b1d103d","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_f40df86efbf8ad09b21ec4230b3cda7773e0666b47391dcfb1c173ed1b1d103d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9aca7a16aa08063a1719e2c06688529b9e34b5464fdb6f0536ab1015e616ae33","published":"Tue, 28 Jul 2026 00:00:00 -0400","receipt_hash":"9aca7a16aa08063a1719e2c06688529b9e34b5464fdb6f0536ab1015e616ae33","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":"9aca7a16aa08063a1719e2c06688529b9e34b5464fdb6f0536ab1015e616ae33","observed_at":"2026-07-28T04:43:08.282317Z","parent_run_hash":"23a1ef85134515049ced29518443d084afc46fd7c967741e6c6acdbdbbf29939","published":"Tue, 28 Jul 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:2607.15166v2 Announce Type: replace \nAbstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a synthetic benchmark and failure atlas built by a clinician. The resource labels medical AI errors by severity from 1 to 5 and safety gate type: missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, and source support gap. The current public release (v0.2.1) contains 44 synthetic cases reviewed by a clinician, with severity annotations, a public Hugging Face Space source, a safety gate taxonomy, a clinical severity rubric, and an automated pipeline for archiving model response screening runs. Forty cases have a populated safety gate field, and four require gate completion. No patient data, clinical validation claims, or model rankings are included. MedFailBench is released under Apache-2.0 and CC-BY-4.0 an","title":"MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection","url":"https://arxiv.org/abs/2607.15166","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.15166v2 Announce Type: replace \nAbstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a synthetic benchmark and failure atlas built by a clinician. The resource labels medical AI errors by severity from 1 to 5 and safety gate type: missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, and source support gap. The current public release (v0.2.1) contains 44 synthetic cases reviewed by a clinician, with severity annotations, a public Hugging Face Space source, a safety gate taxonomy, a clinical severity rubric, and an automated pipeline for archiving model response screening runs. Forty cases have a populated safety gate field, and four require gate completion. No patient data, clinical validation claims, or model rankings are included. MedFailBench is released under Apache-2.0 and CC-BY-4.0 an","title":"MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-28T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.15166"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:df69294791df94b62978b65644cfcff8af69a5672d325622b5e26fd17c1f0f7edac6977c903a2cdf79625d364cdadf89ea65545bf78686ae775b607bafd07805","signer":"crovia.substrate","subject":{"observed_at":"2026-07-28T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.15166"},"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":"2d96db4153d3259f154f4f2ee0cf74e519cb7ab560c0cf610899a5b05cf48dd3","leaf_index":360749,"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":"012d6e2c88454cd2fb0a470d935a58b1198eb060816b354ce2c8bff5e587427d","side":"left"},{"sibling":"825dd1e7da52c405ba71ad965abd2bba71a92248efe4d3f365d03caf4cd88ee2","side":"right"},{"sibling":"d9e0a79a5e926802accdefd58d6ac68d1a723e10528cd6cee1eee08feaf8fc0b","side":"left"},{"sibling":"ef4f800e2e1504434fa359495ae8a2c40cdbc1ddcee7fb29ca8e516464a265b5","side":"left"},{"sibling":"50c235adaddceb608955a24e62ab3bfcd5bcf53f51aaa4b4af7def9f791cecaf","side":"right"},{"sibling":"e13d374e19c0934ab86c2ab592057d967e4dc46b56814627492796afdca9ce68","side":"left"},{"sibling":"c055cde9457517dcbc597b5ba365b33ee313ae69f23793917b237a63c02a9c03","side":"right"},{"sibling":"80654268ff95f1daa72785465b969eee9ea2b22da6f8dfc0d2cf6148d4718a52","side":"right"},{"sibling":"f05fa4d2088913dc5410109b6c9f2c28b5e413f06a98f46cd68973c567c3b416","side":"left"},{"sibling":"fe03c6d0b083c4097049d7fc6d7d08dfdb05d9c198b2786336689712d66eabf0","side":"right"},{"sibling":"590ea76fdfc1b9e8072055c378be3182f916709e8d06bd955232e650a7188b86","side":"right"},{"sibling":"d92781c59301ffd5bfb0bad75d9fdf6d73879f715518149d383f7362213e0daf","side":"right"},{"sibling":"f315303d4402b57497416d48eb4c4bb50405b40862d41c7caf318cb3d29c5237","side":"right"},{"sibling":"36973eb5f586cd67e0c0dc055dd87e734aa544c35d4400d2c9f932f8ef8fb27f","side":"right"},{"sibling":"e39f7900355489c4718b21cc2d3d06382e1d2f22b864d10be9ebc9d498b279a1","side":"right"},{"sibling":"1f9a970b25dd938c98cabc9e0a55c5a6f46292b9fa37cc89d90ef0cbb1e05a8c","side":"left"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"3b50864499c874394ea0928567747666eaf59b01380e46cd52164ec5acec0f71","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":361008,"merkle_root":"3065e8369ea437c06beba806dc4e4bb159979adeb21fe632242c1906a7204647","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260728T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-28T05:38:48Z","sig_algorithm":"ed25519","signature":"9141644407577a82611c1579110f667de2d46dc6b93c6322edf26f4c3056ea99f0e56502853908e30d87c38bcf95eb6e0ab5130525aa51505bd6f61938120609","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_f40df86efbf8ad09b21ec4230b3cda7773e0666b47391dcfb1c173ed1b1d103d"}}