{"_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_80c3760251bafa5037d65581a402cf0f13a4520cf36aec4e1423fcc390616209","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_80c3760251bafa5037d65581a402cf0f13a4520cf36aec4e1423fcc390616209","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"d4589fc99898f7832edfb31947311acefe752f7b661e657c0ead667bb7bcde7e","published":"Fri, 03 Jul 2026 00:00:00 -0400","receipt_hash":"d4589fc99898f7832edfb31947311acefe752f7b661e657c0ead667bb7bcde7e","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":"d4589fc99898f7832edfb31947311acefe752f7b661e657c0ead667bb7bcde7e","observed_at":"2026-07-03T04:43:38.241623Z","parent_run_hash":"f0e30469786257a5e74170498cacb4c028623bf32d6d06d4dbadc488960545be","published":"Fri, 03 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:2607.01470v1 Announce Type: new \nAbstract: Clinical protocol-execution tasks -- checking a lab value, applying a threshold, placing a correctly structured FHIR order -- are natural candidates for RL from world feedback: once clinical SMEs encode decision logic into a verifier, that verifier grades unlimited rollouts without per-episode annotation. But applying RL requires a sound feedback channel and sufficient base capability. We audit MedAgentBench v1/v2, find a 41.7\\% silent-finish ceiling that makes inaction the RL dominant strategy, and construct \\textbf{MedAgentBench-v3 (MAB-v3)} (508 tasks, 8.9\\% ceiling). Training Qwen3-8B exposes two structural barriers: a \\emph{capability ceiling} (10/20 task types have 0\\% base performance, zero gradient) and a \\emph{format-knowledge barrier} (3/20 types require exact clinical codes undiscoverable by exploration). Pure RL reaches 18.2\\% pass@1 vs.\\ 34.1\\% for rule-based SFT; the 15.9~pp gap is attributable entirely to these barriers. A","title":"World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments","url":"https://arxiv.org/abs/2607.01470","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.01470v1 Announce Type: new \nAbstract: Clinical protocol-execution tasks -- checking a lab value, applying a threshold, placing a correctly structured FHIR order -- are natural candidates for RL from world feedback: once clinical SMEs encode decision logic into a verifier, that verifier grades unlimited rollouts without per-episode annotation. But applying RL requires a sound feedback channel and sufficient base capability. We audit MedAgentBench v1/v2, find a 41.7\\% silent-finish ceiling that makes inaction the RL dominant strategy, and construct \\textbf{MedAgentBench-v3 (MAB-v3)} (508 tasks, 8.9\\% ceiling). Training Qwen3-8B exposes two structural barriers: a \\emph{capability ceiling} (10/20 task types have 0\\% base performance, zero gradient) and a \\emph{format-knowledge barrier} (3/20 types require exact clinical codes undiscoverable by exploration). Pure RL reaches 18.2\\% pass@1 vs.\\ 34.1\\% for rule-based SFT; the 15.9~pp gap is attributable entirely to these barriers. A","title":"World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-03T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.01470"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:6862d64ab0084844aae54aae12da902cc6eef9e38fc46ae2354f62972cde39131f25dda799a003210b222784c4efa5705d83682cc07e17a98a8cbfe610034a06","signer":"crovia.substrate","subject":{"observed_at":"2026-07-03T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.01470"},"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":"003fcec4ef8f3e235fbf9e2198ffa91ea07a28164c1a993d2aed951496e9de63","leaf_index":275343,"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":"5fea20f03afe46365dbbd153a67be09ba964b554fd85fd61d30cf2b32bc8f1d7","side":"left"},{"sibling":"a12cf85a9c6aaeea2f7b5e30e42e57d8c7a8934f70af8f1cb3efc4fca19e8efb","side":"left"},{"sibling":"421874cc335c4fa3d1448e8cc0c1f151c1184918bb9c862300c1202e54b4375f","side":"left"},{"sibling":"8e8d066d7465b167085d65e8702b7d22d1c503feec1fe78e51e026fc671dd4df","side":"left"},{"sibling":"005d65808d4c043f04e12c701438cc8afec3b1d8323b862d1368151c3e76809c","side":"right"},{"sibling":"b08b6abe334210fa93c8ff98b879ec0c0d19a9a4a6d894942756c60b1eaf5240","side":"right"},{"sibling":"90e9fb2a20374342836f11695e291756a1f8a0197a80f5da7958594a976dd668","side":"right"},{"sibling":"fd055e725b36f5bebbaeb18583f9d7011c4d8c2a608a11cbd2c166cd895e7a85","side":"left"},{"sibling":"e1a65581e9d68211aa8ba0d138c8d2a4e80afd551e6d1b00c4575c39085df705","side":"left"},{"sibling":"92c062f377cd53076b8dfe55c25ab217059e20113433673cc5747b9348b07e01","side":"left"},{"sibling":"e36f7633c67452f41a7377a7bec9b2d454442688d26539321eebf92cae9db0f0","side":"right"},{"sibling":"4dbd8247ba08a5432c7d6540711da9acb2f59e6189865aa8552dee37f69286a9","side":"right"},{"sibling":"41cd1885dc3fcb51e49eeb887d6d22ec2cfa58df0e4f8d7c7dddf3a1b0ce8249","side":"left"},{"sibling":"8a09562f6b247c1c3cd1fea36cb3b8f1cf5c575479dd514573856a380a964bf5","side":"left"},{"sibling":"723981908169653ca6d835aa9b8381a8c7ad3e3e3830d0792bc32032cda615ee","side":"right"},{"sibling":"c0594fa1ee81d5f019cccc7b5e51af603c6d7e43995498c451012060c7d06165","side":"right"},{"sibling":"4de6a2fb22efbb50c84dc62abeb0f2cbc8c663a9540aeba9e758ebfdfe3e86dd","side":"right"},{"sibling":"fdbb3519f8dc411a4043dfb5abdbfea5441e130326183ac2247c42584033f152","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":275799,"merkle_root":"2581d0d6e5fa345cdf2e8ab3b191ace76d6b14189901ab0e4c2291ca1d1ae1e6","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260703T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-03T05:38:09Z","sig_algorithm":"ed25519","signature":"e44a386a5ae00c0e7fc67b1179bb9060bf0fefc006e454fec70e27668182ff497d1e2faf0c3b22de0917beefb7c80e880dae925a3f67e1b16aa0eb44bf947407","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_80c3760251bafa5037d65581a402cf0f13a4520cf36aec4e1423fcc390616209"}}