{"_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_faa8bab686af48578d2632e43a365cf42236edd495cbce93c28130b2c503a203","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_faa8bab686af48578d2632e43a365cf42236edd495cbce93c28130b2c503a203","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9ab40a5c14736964f1ad8e1acc91b4bbd17b65ff9b7c0a9bf551f01eec3b9a67","published":"Mon, 29 Jun 2026 00:00:00 -0400","receipt_hash":"9ab40a5c14736964f1ad8e1acc91b4bbd17b65ff9b7c0a9bf551f01eec3b9a67","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":"9ab40a5c14736964f1ad8e1acc91b4bbd17b65ff9b7c0a9bf551f01eec3b9a67","observed_at":"2026-06-29T04:44:03.414425Z","parent_run_hash":"36b5ab5c57ae76dc9e1a863501c4d38f172868cfae31b4ba5baf3caffaafb2c4","published":"Mon, 29 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:2601.17642v2 Announce Type: replace \nAbstract: Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model's ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-o","title":"Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context","url":"https://arxiv.org/abs/2601.17642","vendor":"arxiv_cs_ai"},"summary":"arXiv:2601.17642v2 Announce Type: replace \nAbstract: Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model's ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-o","title":"Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-29T04:44:03Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2601.17642"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:27de329e08d78d811b1a6918c170ec2a4292bb6ef1f4a4fcbccbd640962a0cd637f722096b86a6b2ff5c399a81a0cdf63bee11be73aa23ac4b0212ce11bf5e08","signer":"crovia.substrate","subject":{"observed_at":"2026-06-29T04:44:03Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2601.17642"},"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":"a26179e44c91d4739837ae26544245db5729a108556483d0cdc2323712d311c7","leaf_index":261453,"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":"950041c325ad51d2d3cf8394a78cc3fa8282e77fec9f8092cdf489bc120a81f4","side":"left"},{"sibling":"254bb0f2525a05e362b54e7d9a24bc56b48055daa166be97ac6191d2bb453e37","side":"right"},{"sibling":"c28283cb74aa7e1bc93e3fe696e4f1ab2d3b595cf772a4c1e70c6526c8aba9e1","side":"left"},{"sibling":"3125f4e9099d50189469fbcaa8d679cda2c821046580b77750db6b3d65815fef","side":"left"},{"sibling":"b14634321bd4e6143c44cc26a6933b5e4af91fdff153839239c38982d8bec179","side":"right"},{"sibling":"6964c7fbbb2e4940d0c2ddfcfef79a2a9e7d53aa2f229440f53a7577177c532e","side":"right"},{"sibling":"a600c67ab28d0232fe4727e4641fc665bde749779b50edf849b1a9c8287bc809","side":"left"},{"sibling":"4b4bda5fa1fb23989b8f6f192c36dadc8266c378c69d42945af35c9d6ab81a10","side":"right"},{"sibling":"6d1df65d14253ed3a13c03e25aa9adcd9a091d8062a82e8586bcaee74013b90e","side":"left"},{"sibling":"9f9daa9d12e65b219f34c92aec45450536b79a42b8892050d66961432ae28ed1","side":"right"},{"sibling":"b5725d7b0807dc6da32d9788f20057fa8726be38d30a9ebdabc605ae92739122","side":"left"},{"sibling":"e321b2cac14cbe28f76ccb7938249a40ff60cd5d2128b5634be046ea10e984b8","side":"left"},{"sibling":"5900dc6c7d13855af9d0385baf1691ec386df33e450c422af1cabe0a36e40ad8","side":"left"},{"sibling":"ae636ddee98c71ab7a7dc55ddfab70c7f710a2b6abfdf7a8b5d16a4017d1c0d1","side":"left"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","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":261662,"merkle_root":"aa8865c239aa2eb6c8aa7c6250f56b3cd5709854a8a07f6a29eb4ddd8802cb6f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260629T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-29T05:38:02Z","sig_algorithm":"ed25519","signature":"476329233e82fb35fba2552ddc5d1d75b2bdd8513bbd281e9c40a0b8e475df374a62dcd8b456b0c5e8815984f5b4bf0983ae95d2cf4d7412ebb13a433b933c0a","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_faa8bab686af48578d2632e43a365cf42236edd495cbce93c28130b2c503a203"}}