{"_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_efd966a60348e2ddc72173ab51c5b5317ba857554b9a02fd13ac40f44bf66356","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_efd966a60348e2ddc72173ab51c5b5317ba857554b9a02fd13ac40f44bf66356","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fcb5fbb41d24dc6620a41f91b262bc9561df910d112a25bb21baae9aa8be0cac","published":"Wed, 22 Jul 2026 00:00:00 -0400","receipt_hash":"fcb5fbb41d24dc6620a41f91b262bc9561df910d112a25bb21baae9aa8be0cac","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":"fcb5fbb41d24dc6620a41f91b262bc9561df910d112a25bb21baae9aa8be0cac","observed_at":"2026-07-22T04:43:18.261256Z","parent_run_hash":"4765c85b8b4b27ff9a690c1ae11c3b009baa2c60297295f395ad422f5afed68c","published":"Wed, 22 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:2607.19321v1 Announce Type: new \nAbstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such approach: rather than trusting the agent, it treats it as a potential adversary and uses a monitor to detect covert sabotage before deployment. We evaluate AI control for automated AI R&D with ResearchArena, a framework spanning four long-horizon tasks: safety post-training, capabilities post-training, CUDA-kernel optimization, and inference-server optimization. Because the deliverable in AI R&D is an artifact that will be deployed and run, we pair each main task with two kinds of hidden side task: an embedded side task that sabotages the submitted model, adapter, kernel, or server itself, and an independent side task that takes a covert out-of-scope action in the sandbox while leaving the artifact honest. We evaluate frontier agents at both sabotage and monit","title":"ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D","url":"https://arxiv.org/abs/2607.19321","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.19321v1 Announce Type: new \nAbstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such approach: rather than trusting the agent, it treats it as a potential adversary and uses a monitor to detect covert sabotage before deployment. We evaluate AI control for automated AI R&D with ResearchArena, a framework spanning four long-horizon tasks: safety post-training, capabilities post-training, CUDA-kernel optimization, and inference-server optimization. Because the deliverable in AI R&D is an artifact that will be deployed and run, we pair each main task with two kinds of hidden side task: an embedded side task that sabotages the submitted model, adapter, kernel, or server itself, and an independent side task that takes a covert out-of-scope action in the sandbox while leaving the artifact honest. We evaluate frontier agents at both sabotage and monit","title":"ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-22T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.19321"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:625472d4c175b25e14914fd536eaabaa6fbc985b58443315a700700d11e52649ab3709f9ec7b94a69b6204a72d82814796237cf3b807005da0ac0a296a90140a","signer":"crovia.substrate","subject":{"observed_at":"2026-07-22T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.19321"},"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":"d2c4c1500b00779af55135583260e28947835993b1188e6e2b6739871e3d1053","leaf_index":340184,"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":"549cadbbc1008a3713ac6fea958d9e0babe0a695d7a1e6fee9944754065dfba0","side":"right"},{"sibling":"e5aa1eee68f5be90081993f18306d31f5c609f49a574819cc1f4ce6dc92a0a9f","side":"right"},{"sibling":"669addfdd4ca52e6374ef94bf6bacb60e2eba7c00b630fc8b7f3cacd04276534","side":"right"},{"sibling":"97328259fd79f7f13dc236828ba1c62c401731a0f02ccf43e684301d5071d719","side":"left"},{"sibling":"af191e4d6d78aef8a24d4bef0bfefe3c19d673ccfed9f1c3e4c072013234335c","side":"left"},{"sibling":"08f669cf62f9d6d640804bc9893be0035eaa2efdd5e539b9010e2fc83200caac","side":"right"},{"sibling":"3ef60c9ed8999dfaf391c6bba67940285b69f69ba30251f62e74b5bc37deb1a8","side":"left"},{"sibling":"acd872eabf3ff3deb3760bc63ca3a4ca483306d9b2eb2ddf59ac880a653ae17a","side":"left"},{"sibling":"c0cb3fbdae423fd11084f7ab87b57c412a0ef2e6dcda395ebb9831d480ad609b","side":"right"},{"sibling":"c7fc9d4187cdc36f4c03b4b13daf4b880ea65536b051f71a5cc2543839d02697","side":"right"},{"sibling":"1758ec6ac206ce40e8368cb702195322fe3737d0fb03d8bd9e3b30acc4fa7d81","side":"right"},{"sibling":"0c407f0d553cf3fab8f9bd79205b8180e090cbf29fa0490ebb55155041ad5c86","side":"right"},{"sibling":"2dd9cb2521044ee7c6b74f2315e0a0253b8df0d04a7b810bbbbe7da5a9788769","side":"left"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"787ee3744642ff909d610b0514cb100784f0ef1ba0ef4c70a0dc91f0ab2bb192","side":"right"},{"sibling":"9fc8a8ebbc1bff7e62b9f1e1c681c91e7196092ce9551573df6e23096df13e4d","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"ee6f33920899d9bdef2eb706dfff29e26eea61e29ea9824c6c8e6bcd48275d76","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":340557,"merkle_root":"7d45d94f20b5bf82263df45b87749e19e06161972f25141dd573cc138d566338","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260722T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-22T05:38:39Z","sig_algorithm":"ed25519","signature":"812cb61e90d3582ba508db8515c4168bbf8ee1c6762885609049d012f680f8068f15c98b9accf2042047dcfc6a6fc3885820ee34b0be350846386f64f2591309","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_efd966a60348e2ddc72173ab51c5b5317ba857554b9a02fd13ac40f44bf66356"}}