{"_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_8761a37fb3a297530d50e83ad479721ae22a0faa7f61c129f77b7c98b24c7bab","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_8761a37fb3a297530d50e83ad479721ae22a0faa7f61c129f77b7c98b24c7bab","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7858c19095f874f6165aba00b6e0cdc37bdf8076c0f6bc66859c0770e815af52","published":"Fri, 17 Jul 2026 00:00:00 -0400","receipt_hash":"7858c19095f874f6165aba00b6e0cdc37bdf8076c0f6bc66859c0770e815af52","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":"7858c19095f874f6165aba00b6e0cdc37bdf8076c0f6bc66859c0770e815af52","observed_at":"2026-07-17T04:43:38.280949Z","parent_run_hash":"113193614a8af99887180226d4e28a8b71d957da5fe3694f0e7a56807c145504","published":"Fri, 17 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:2607.15166v1 Announce Type: new \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 clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, source support gap). The current public release (v0.2.1) contains 44 clinician-reviewed synthetic cases with severity annotations, a live HuggingFace leaderboard preview, a safety gate taxonomy, a clinical severity rubric, and an automated pipeline for archiving model-response screening runs. No patient data, clinical validation claims, or model rankings are included. MedFailBench is released under Apache-2.0 and CC-BY-4.0 and carries the Zenodo DOI 10.5281/zenodo.21205535.","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:2607.15166v1 Announce Type: new \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 clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, source support gap). The current public release (v0.2.1) contains 44 clinician-reviewed synthetic cases with severity annotations, a live HuggingFace leaderboard preview, a safety gate taxonomy, a clinical severity rubric, and an automated pipeline for archiving model-response screening runs. No patient data, clinical validation claims, or model rankings are included. MedFailBench is released under Apache-2.0 and CC-BY-4.0 and carries the Zenodo DOI 10.5281/zenodo.21205535.","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":"2026-07-17T04:43:38Z","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:a3859bca5c1cd94eeb36f4359d5ec26fde74e6dc43fc79ba71ab1880ce8256ffdf79b37925399d87091d9ce9402833f840b7ef005af55554d0265adb5ad6d900","signer":"crovia.substrate","subject":{"observed_at":"2026-07-17T04:43:38Z","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":"aa77d673afa602ea67668f8254b0f7402f7ca80c871f8244cb212e9f9754a0af","leaf_index":323045,"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":"be99c81ac62b01980da9baf7eb069e8426b18056c83411ce1c6bd76985ac928b","side":"left"},{"sibling":"da2e98d93f6e806db8e042398810696093e34e68da84a2506cff48b994b6c0d0","side":"right"},{"sibling":"97ff9f34c0e4da7395a84c055ae5993b0a1bd248f4707dfe9d65648ee8f385ce","side":"left"},{"sibling":"188bbebaefea708fc3d77ec4c7cf2215f203aa206401a438cf899dfdcf075e3f","side":"right"},{"sibling":"ede0f9d78db7a7c9aa2547375a9f112043130139ad163f470b3c9b8c3cff1f42","side":"right"},{"sibling":"f4935e2c2f77b7da9433b98e135fe5e3ce776c72aa0f30e9f3f0db9633de8e85","side":"left"},{"sibling":"fa46cdb7cb881d614aa37b466168cf41201fba62306710750ffddfb495240293","side":"left"},{"sibling":"5944e6d0988d989a4ae4330320fe2633624339ee8db50eaa0d3fe8981ac982cf","side":"left"},{"sibling":"e90a96bd60cc2aad32b2969366989aa5d4e0c71aeb240044c7778cca7188dc3f","side":"left"},{"sibling":"d7e66b08e4f129ea3ff266d25de4f974fe1f0d56e2fae2a6d3ae1e1565007da9","side":"right"},{"sibling":"05a09763743cdc09fc45cf454e4e3ea4a0d1cd74f9c8162b2a57e2c873160908","side":"left"},{"sibling":"de3120ef2488b8a791a686b47257da4e612256abdfcdda7519265e7edd47d041","side":"left"},{"sibling":"e86f56a4883492da5b5e7b0201324c52946e865e69b99ebb532f41fe3c658ee4","side":"right"},{"sibling":"34d85f6ad6cc7dfa79d90e2b9ff99a561bcdc75b0301bbbd3e83861f54535c1e","side":"left"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"9b11714124b9b951ff9450b0ee9d625a0b70b6da2cf388bd3df1475eec0b17ba","side":"right"},{"sibling":"a4523a9014d45df43e006e9210a73428c380d771f2c650a1b986910759b0cdf7","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":323382,"merkle_root":"2f4d32419c80a9600aba5a480fc3fb7012ec0a695c91a1b055048e78760b65ca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260717T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-17T05:38:31Z","sig_algorithm":"ed25519","signature":"495308c7bf004117807331d3f71d0b079f6bd7ed7737faa58c773b1b3e80ee84928d2d8519cc7d2b809506501aada1be6546f72c7ecda3dad5445cbb44502209","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_8761a37fb3a297530d50e83ad479721ae22a0faa7f61c129f77b7c98b24c7bab"}}