{"_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_c810efe4dad1be0d5c581cb44c0d54afaf1ec6935b04e6dbc2a6011d4e0a5e3c","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_c810efe4dad1be0d5c581cb44c0d54afaf1ec6935b04e6dbc2a6011d4e0a5e3c","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a17dedcb88d272d53599e5afe5c951a964891d0640a3567a8d957c2f578a33ba","published":"Wed, 08 Jul 2026 00:00:00 -0400","receipt_hash":"a17dedcb88d272d53599e5afe5c951a964891d0640a3567a8d957c2f578a33ba","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":"a17dedcb88d272d53599e5afe5c951a964891d0640a3567a8d957c2f578a33ba","observed_at":"2026-07-08T04:43:57.834712Z","parent_run_hash":"46ab019f0b0f0bfcde5e14ed7c256069c6fa8c8079b9f87fd3a8a6d9259e3864","published":"Wed, 08 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:2601.22136v2 Announce Type: replace-cross \nAbstract: Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmark that treats detection timeliness as a first-class metric. On 9,429 incident-grounded code-agent trajectories, we define the Early Intervention Rate (EIR): the fraction of detected rogue trajectories where the alert fires within a k-step window after the divergence point, isolating timing quality from coverage. This metric exposes what we call the Forensics Trap: a pattern-based guardrail with 847 rules achieves 86% recall yet is statistically indistinguishable from random timing on EIR (0.23 vs. 0.24; p = 0.66, one-sided binomial; difference within CI), because over three-quarters of its alerts trigger on benign prefix code before any violation occurs. The 4x EIR gap between rule-based and semantic detectors is completely invisible to accuracy, reca","title":"StepShield: When, Not Whether to Intervene on Rogue Agents","url":"https://arxiv.org/abs/2601.22136","vendor":"arxiv_cs_ai"},"summary":"arXiv:2601.22136v2 Announce Type: replace-cross \nAbstract: Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmark that treats detection timeliness as a first-class metric. On 9,429 incident-grounded code-agent trajectories, we define the Early Intervention Rate (EIR): the fraction of detected rogue trajectories where the alert fires within a k-step window after the divergence point, isolating timing quality from coverage. This metric exposes what we call the Forensics Trap: a pattern-based guardrail with 847 rules achieves 86% recall yet is statistically indistinguishable from random timing on EIR (0.23 vs. 0.24; p = 0.66, one-sided binomial; difference within CI), because over three-quarters of its alerts trigger on benign prefix code before any violation occurs. The 4x EIR gap between rule-based and semantic detectors is completely invisible to accuracy, reca","title":"StepShield: When, Not Whether to Intervene on Rogue Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-08T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2601.22136"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:7382da8bf20639a9a95fb647796c81f22ab5f459cb303b2363aa7df218d7e3d787722503e1008ec22f28d55ae8938e04e0aa280e625bb51cafdecd13730e0b0a","signer":"crovia.substrate","subject":{"observed_at":"2026-07-08T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2601.22136"},"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":"25fbbbc39928ea8fdef3382c5970729be6ecc032cfdde254162ee4cb29285d92","leaf_index":292839,"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":"851136bbf53dca25b20783c826ea8b37586717d1aac2a9d8c2ab4d27075b0a62","side":"left"},{"sibling":"fe2a08dd8fa8ba28e7c338738f5faeafe6956620a75da0d3598401eb148b9b74","side":"left"},{"sibling":"90a13c51299e2976973a7d4be3ef67cfc4f9920a78cd1bc289b9857b00ababd5","side":"left"},{"sibling":"fc7c38d5613569213dff8886feeb3cc2983517d8d5c459933714bcd84b282f64","side":"right"},{"sibling":"0202c453a3948e9013eb5a6cb389c144d27f22e10ea2037f465ba4bfa492d55c","side":"right"},{"sibling":"2209adb7e32bdc00faa3455b10e6e84ea7382544d1d0331dbeed97777453e5be","side":"left"},{"sibling":"b68effed96c9c760c6a644ba421552cb75cab0f5269153819ebc6ee58c6e16f1","side":"left"},{"sibling":"6e4b9570930ece9a9ba8eab260493982ccceb0060de1dddb4ef505f9f3d00598","side":"left"},{"sibling":"1515812edbf9903d3d787f20218b8577e2f1fef32592508ce01a3b3ebe75f507","side":"left"},{"sibling":"d4b475beae71e5b4d5ab7e66f7144e7b8e1356fcd32339e49df234b455659fef","side":"left"},{"sibling":"cead64e0790e8871aeea2334210146b5e35fe7e4bc10748acdf76da0c565be05","side":"left"},{"sibling":"d1231ac6e6bd7d6867a9109fbdadede0b1631e97866ddde70f7ac2d52c28e15f","side":"right"},{"sibling":"76855b4804c75c52bf97aa34358950d42d6103cdc1a86be5f0a2c8de4d65c106","side":"left"},{"sibling":"a75ab4319e241beeddb1b3f5705febe0422937926c3479923ccfb0b0082fa4e3","side":"left"},{"sibling":"bd04fa605f883bfb2b81510d045b1e85e555a03da3be083619f61384dfe40ff8","side":"left"},{"sibling":"9e75f2ab0ddf2dc9e92af7049244c21b909734ab57906a35dfad2853ca9966e2","side":"right"},{"sibling":"e6cd4cad39a4b6ca6647d1b0ad2db86e57e5fa6240f65966c10093e91140769b","side":"right"},{"sibling":"90a7efc6b94ec8913fbdf03f4927a821b9fb89921d526716f5ee28f015303779","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":292998,"merkle_root":"f533b7efebdfd8fb6ba3e7cc158ee55261fd53a7985f234cfea359170dad4d5a","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260708T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-08T05:38:17Z","sig_algorithm":"ed25519","signature":"07ebb10c732bbffb28b55a5db01d5525f6b8ab7ef36e1e0a68c35c96ded99f7040c277edba75eb6b15c77feda30bd5321e31ada6f572b674d06f4f8e24bd2f07","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_c810efe4dad1be0d5c581cb44c0d54afaf1ec6935b04e6dbc2a6011d4e0a5e3c"}}