{"_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_4df72a82474f5066844e7178dbb5fb75af7bf62d251540919b355a7c037c27ca","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_4df72a82474f5066844e7178dbb5fb75af7bf62d251540919b355a7c037c27ca","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7b23db9dcaf8201310a1f49b26a024259357c09355fd7ca72edd13630c607d65","published":"Wed, 15 Jul 2026 00:00:00 -0400","receipt_hash":"7b23db9dcaf8201310a1f49b26a024259357c09355fd7ca72edd13630c607d65","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":"7b23db9dcaf8201310a1f49b26a024259357c09355fd7ca72edd13630c607d65","observed_at":"2026-07-15T04:44:03.592429Z","parent_run_hash":"d49a6cf532e74153266f377b7760fc948d950d80ed41fc3e3eb82b58f5597ead","published":"Wed, 15 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:2607.12469v1 Announce Type: cross \nAbstract: Many agent-safety evaluation results are not yet load-bearing evidence: identical nominal outcomes (task success, attack success, monitor scores) may sit atop materially different evidence regimes. No vendor-neutral, runnable instrument scores reconstructability as an evaluation-validity metric: whether captured evidence can reconstruct the decision a claim depends on. This paper introduces a property-level reconstructability metric over eight decision-property classes and a cross-harness adapter emitting per-decision Evidence Sufficiency Cards backing a per-run monitor-coverage release check. It specifies a counterfactual-replay intervention protocol, implements its replayability-precondition probe, and defines a claim-evidence overclaim gap. On public and bundled traces, without new model runs, twelve-field sufficiency spans 0.458-0.833 across four inputs sharing a surface reading; replay preconditions are unmet in every scored trace","title":"Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric","url":"https://arxiv.org/abs/2607.12469","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.12469v1 Announce Type: cross \nAbstract: Many agent-safety evaluation results are not yet load-bearing evidence: identical nominal outcomes (task success, attack success, monitor scores) may sit atop materially different evidence regimes. No vendor-neutral, runnable instrument scores reconstructability as an evaluation-validity metric: whether captured evidence can reconstruct the decision a claim depends on. This paper introduces a property-level reconstructability metric over eight decision-property classes and a cross-harness adapter emitting per-decision Evidence Sufficiency Cards backing a per-run monitor-coverage release check. It specifies a counterfactual-replay intervention protocol, implements its replayability-precondition probe, and defines a claim-evidence overclaim gap. On public and bundled traces, without new model runs, twelve-field sufficiency spans 0.458-0.833 across four inputs sharing a surface reading; replay preconditions are unmet in every scored trace","title":"Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-15T04:44:03Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.12469"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f7750f613ddbafac2df70d2ffb18fd033d60914215baca24377208bcca84311035807bf2be43a77294bb71a687e4af3cc32c15d5f060bf58013dcf0c5d3f2e0e","signer":"crovia.substrate","subject":{"observed_at":"2026-07-15T04:44:03Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.12469"},"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":"0a2c36c44af90e9f6f24fcaada5ab286360ab71a4dc62d87895e65ea8f4eab67","leaf_index":316477,"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":"eeef7053de7e1a9834f0ce0b61bc6346fa7ae1dc49ad635148930b665f5e79f2","side":"left"},{"sibling":"82873f77e61cddda17d08c5e913f085436a0ca44cf5929564a3ce0fef9dc8707","side":"right"},{"sibling":"6bac642e2d3dc6d2a290b2cb1dce29c3547df511c5062a1c5c209f6e8959e4a1","side":"left"},{"sibling":"befc97141432b72da906e07c58148bbaf88e1e9fbef5a42bd161022e59ac2239","side":"left"},{"sibling":"f488f475c63d249d4d0786e065ea5eb46347e265918e1cdb2e808b57922d2f59","side":"left"},{"sibling":"3b8fdc38ff056d4917ee1a0f47d25900d462aa81d7c98417e1e574385685b15c","side":"left"},{"sibling":"7ea54d26dd378975e8412c96c63f11ce7eb04515c5676061d25695229e6c6c97","side":"right"},{"sibling":"c07de1952926cdb34af34c5c0baaf9021a0ab704be6665431e37a7c145fca4d5","side":"right"},{"sibling":"1c7f1bf97993e3a126824f8350788b168c4c13264fb03a73b3ede312035d3527","side":"right"},{"sibling":"84a7590e6b24dd07ed46597f19deb75d9ad247b4227b17f30857ec7cc0fc5c21","side":"right"},{"sibling":"c8d3d8cb0183b912107f9781ad2a1b6c0c9424906c5907c09deeb5bea9d7b571","side":"left"},{"sibling":"0cb62c0ada57a2406a6bcb100889d3e8b29a15efeed07adaff5bb90a5e80612a","side":"right"},{"sibling":"0b69289b25462ddd6166f6f49004cfc8ada0ab4f10adafe188347817bdd46e37","side":"left"},{"sibling":"1418b281cd985b5ed411ef25f2017a1826cc14919b6fad3934e6ceeec693699b","side":"right"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"abe4a8c706e530484d1e96a8988cb09eab85928b2050985500ab289753fe3eec","side":"right"},{"sibling":"f436dccf82aa2c1eb7bfa3eb84316e116aaf64dc55cd9592597118f6cb0648f6","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":316730,"merkle_root":"a8e6e5be81ea6f5b5f2227422459bf39455fe9f0b6602b4d1ce6977dbfd78bc7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260715T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-15T05:38:24Z","sig_algorithm":"ed25519","signature":"df1678d268b5a07413e2ca6e748c3f40b6cfedea930a18d843489a4ab513da791bf0a886caab1b918d0989f8ebaaf3d0035ca2aa777913b1ad29979f1deb9a0c","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_4df72a82474f5066844e7178dbb5fb75af7bf62d251540919b355a7c037c27ca"}}