{"_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_9d3fd7094e3b5ca4fd311bf112c348f965aab0a79fea1c8e38b2d2e6c9c18463","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_9d3fd7094e3b5ca4fd311bf112c348f965aab0a79fea1c8e38b2d2e6c9c18463","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a7c23da9a4a5f7869a847711a5d870d6eeb67c292afa47c6fb56c94b5afaaf4f","published":"Wed, 24 Jun 2026 00:00:00 -0400","receipt_hash":"a7c23da9a4a5f7869a847711a5d870d6eeb67c292afa47c6fb56c94b5afaaf4f","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":"a7c23da9a4a5f7869a847711a5d870d6eeb67c292afa47c6fb56c94b5afaaf4f","observed_at":"2026-06-24T04:43:17.877668Z","parent_run_hash":"ca17d06d44ba7db934e6f913874699efc608b8f87453f1ac67f52060e620b57c","published":"Wed, 24 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:2606.24145v1 Announce Type: new \nAbstract: Large language models (LLMs) can produce clinically fluent recommendations for type 2 diabetes while failing to satisfy guideline constraints or explicitly justify lifestyle-related glycemic claims. We present T2D-Bench, a reproducible benchmark and evidence-gated evaluation framework for testing whether LLM outputs satisfy explicit, graph-checkable evidence requirements. T2D-Bench is built on a multi-layer clinical-lifestyle knowledge graph that combines a biomedical spine (UMLS, DrugBank, SIDER), computable ADA Standards of Care rules, and lifestyle knowledge connected through a mechanistic bridge to glycemic laboratory effects. Across 100 structured vignettes spanning diagnosis, medication safety, and adversarial lifestyle conflicts, baseline outputs failed benchmark-defined evidence-path checks in 35% of cases for GPT-4o-mini and 33% for GPT-4o. The evidence gate detects unsupported omissions and uses constrained revision to bring ou","title":"T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph","url":"https://arxiv.org/abs/2606.24145","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.24145v1 Announce Type: new \nAbstract: Large language models (LLMs) can produce clinically fluent recommendations for type 2 diabetes while failing to satisfy guideline constraints or explicitly justify lifestyle-related glycemic claims. We present T2D-Bench, a reproducible benchmark and evidence-gated evaluation framework for testing whether LLM outputs satisfy explicit, graph-checkable evidence requirements. T2D-Bench is built on a multi-layer clinical-lifestyle knowledge graph that combines a biomedical spine (UMLS, DrugBank, SIDER), computable ADA Standards of Care rules, and lifestyle knowledge connected through a mechanistic bridge to glycemic laboratory effects. Across 100 structured vignettes spanning diagnosis, medication safety, and adversarial lifestyle conflicts, baseline outputs failed benchmark-defined evidence-path checks in 35% of cases for GPT-4o-mini and 33% for GPT-4o. The evidence gate detects unsupported omissions and uses constrained revision to bring ou","title":"T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-24T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.24145"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:31aaa217012a31f8e38e6e0d1f218ed2c15e0019f10b667cf6ecf3604fe33b53eca17401195d97b1f7ad120deda084870c07d2fbc88e64c05c7bba496b834101","signer":"crovia.substrate","subject":{"observed_at":"2026-06-24T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.24145"},"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":"30027185e74eb09989343049d127c3bd1d38aeba1c1e07657068e26866941479","leaf_index":244426,"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":"e737e9f8c9dfb3db4f98220bb3bc8aadd6278715bd074a110e995200842a79fc","side":"right"},{"sibling":"5bd391c77b20c07cf33d718fafa0ea399cb4c35375bbadd7327f89de7fe68cce","side":"left"},{"sibling":"ad8a08115cd72918ab4afc9896dd46955b9918ecb28dfb4be092895b6ec39ad3","side":"right"},{"sibling":"0856e3a7707692fdf3187a07e9693205da2a7c3e3404403496b19e9b875fcea2","side":"left"},{"sibling":"85fc1bfec4b2f833d4b4a081e9c03ec374f52e1c08ea81bdc1d4c90703979114","side":"right"},{"sibling":"dff6eb814eef21a759425439431919e533fe3c4c471cf298786ef97d171e051c","side":"right"},{"sibling":"c56732dc17eeb36165904e6852de6bba2b9a84b8469f41c4ec2f52d30d7ec552","side":"left"},{"sibling":"15f48e0a2913d128f60a5e7f790a33afe2bc5de6c7d7d3be71d0b93c1434d471","side":"left"},{"sibling":"2b242921d744c9b6cbe2a988917698dfd00620e46afc5362a806f02ffdd1f721","side":"right"},{"sibling":"bc74ebb08462da8a50fc65ea75f8a8a3418d10ebd471d830f1c67f33dd54dfd1","side":"left"},{"sibling":"6dafd355e5d54c60e61c6c02d3842984e234b1f5bca1623fcdd3def7b8931973","side":"right"},{"sibling":"3107b9d4dbf9456a39f99de694a4dd4da2c0600f9f8855f125161335fe8810af","side":"left"},{"sibling":"86118ab4500c3055a2af70062751a960423c464405b18ca1c37411bf0ce3f52e","side":"left"},{"sibling":"3a42039065acac6d3e4088ec61d9c116ecf7a26c7b7163d23da8fd0b3362e038","side":"left"},{"sibling":"c044f2bd864a0e8e8af5a7f6e3124def7fc4b4511b2b166ea8f9de321e8d385e","side":"right"},{"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":244827,"merkle_root":"274e133c6dfa2781a9cfb85337d01cc6b72688ce5e810149f3183e400ffab136","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260624T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-24T05:37:55Z","sig_algorithm":"ed25519","signature":"22ca3cee4de2447b3d281e30e09fe566461996bb7be4d4465f08a3f4cf59cea58f22683a4aa10ef4d5d17a19b03f4212392bfd26f2b51f289f0cdf1042a03800","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_9d3fd7094e3b5ca4fd311bf112c348f965aab0a79fea1c8e38b2d2e6c9c18463"}}