{"_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_8111a8278e68510b909d7476ec8571c4dc2f124b1b04f48aed108749dffee3e8","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_8111a8278e68510b909d7476ec8571c4dc2f124b1b04f48aed108749dffee3e8","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"34396cf0c79dcf1f3a54fcf68ce97652fef6310fee12d4db9f16ccb0fe959edf","published":"Thu, 04 Jun 2026 00:00:00 -0400","receipt_hash":"34396cf0c79dcf1f3a54fcf68ce97652fef6310fee12d4db9f16ccb0fe959edf","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":"34396cf0c79dcf1f3a54fcf68ce97652fef6310fee12d4db9f16ccb0fe959edf","observed_at":"2026-06-04T04:43:08.243501Z","parent_run_hash":"298818240313a3c9ce3ace3750dbf55845013dc3bc59aeced6331eccefdb61ac","published":"Thu, 04 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:2603.10044v2 Announce Type: replace-cross \nAbstract: A safety score earned on a benchmark need not predict how the same model behaves once it is wrapped in an agentic scaffold the benchmark never tested. We ran six frontier models through four deployment configurations (direct API, ReAct, multi-agent critic, map-reduce delegation): N = 62,808 blinded, pre-registered, equivalence-tested evaluations across four safety benchmarks (BBQ, TruthfulQA, XSTest/OR-Bench, sycophancy), plus three supporting analyses.\n  ReAct and multi-agent scaffolds stay within a pre-registered +/-2 pp equivalence margin; map-reduce delegation degrades measured safety (NNH = 14), though that loss is largely a measurement artifact: on identical items, multiple-choice versus open-ended phrasing shifts the measured safety rate by 5-20 pp, and decomposition silently strips the multiple-choice options. Roughly 40-89% of the per-model map-reduce loss is this format conversion rather than reasoning disruption, and","title":"Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety","url":"https://arxiv.org/abs/2603.10044","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.10044v2 Announce Type: replace-cross \nAbstract: A safety score earned on a benchmark need not predict how the same model behaves once it is wrapped in an agentic scaffold the benchmark never tested. We ran six frontier models through four deployment configurations (direct API, ReAct, multi-agent critic, map-reduce delegation): N = 62,808 blinded, pre-registered, equivalence-tested evaluations across four safety benchmarks (BBQ, TruthfulQA, XSTest/OR-Bench, sycophancy), plus three supporting analyses.\n  ReAct and multi-agent scaffolds stay within a pre-registered +/-2 pp equivalence margin; map-reduce delegation degrades measured safety (NNH = 14), though that loss is largely a measurement artifact: on identical items, multiple-choice versus open-ended phrasing shifts the measured safety rate by 5-20 pp, and decomposition silently strips the multiple-choice options. Roughly 40-89% of the per-model map-reduce loss is this format conversion rather than reasoning disruption, and","title":"Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-04T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2603.10044"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:be8a6243904246bece755e0f7dd889131757dd5a29b4d9509516fee2c0b36b3138bf9d8f039b7f41fb3bc4a98a8e4c34fb6cecea85b14d7def56d98892c54c07","signer":"crovia.substrate","subject":{"observed_at":"2026-06-04T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.10044"},"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":"c49c5b812c0abb1bb516ff9ee53fe9afcd47f6278999047ed8354823cab5a5da","leaf_index":212862,"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":"b519778a776121c86fb304824176e75dc7689d90b4050f50c52b4d136b0162b3","side":"right"},{"sibling":"1f779acc1728ab58f24715e6730d9af45d54ee7824d2a17ea7871347a70bb59b","side":"left"},{"sibling":"15aca30da1ed4c45d8b725d96db5825404b41ca0aad75a09420712f774d5dc8a","side":"left"},{"sibling":"20b8e3f8b7a72a43275b4c4347c821d8783a13b3f5d01234ff078b8ce7cba008","side":"left"},{"sibling":"d565590cc1149806b48ae13003db7d08ad22218dd2194c41b0604800e869e7a2","side":"left"},{"sibling":"5dbe4c69ae1d82e7ce20a81472ef98129cfa7bf7d8810d2abc0d9149c1223414","side":"left"},{"sibling":"a4d720a21c128acd66da32542f5a6516eadd1108045e73ba02163baa0cf221fc","side":"left"},{"sibling":"5d10c089cc50333cc6f5ec8f5c37b251f9cdd4252a9604bb46ec83ac720abdd9","side":"right"},{"sibling":"b4e8a5af3a9fdc4bb815270cd541ee4baf09fb1d9e2cccd75c7346558e1f1e4c","side":"left"},{"sibling":"cfb460164a914d1f96a36aa17124b45bb5417829d2adbe5ca48375dbd842ec44","side":"left"},{"sibling":"a84ebc8e894a9893ee34d1afc942d15f28243b926f1e5f9d7f10a3de1e795262","side":"left"},{"sibling":"f8f6bd9da448fa097e2115b71146f61691d9f8807aca291c87c633192a7224e9","side":"left"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"422bcf7e281ca3a607f3726a5e6b8fabdb85e8b32199b4a86356998e260a0b34","side":"right"},{"sibling":"54a99163a4a62374c3ca6fb46294222f1d4b1a9d0b636e27256b0e093e98239a","side":"right"},{"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":213053,"merkle_root":"19d104b92c4d7299881c447fb8422611fc9cb8615d37a538959e34a2da7ef55f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260604T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-04T05:37:49Z","sig_algorithm":"ed25519","signature":"630748e88645187aa3b4d4cb8c872cc146180d0301e4c6656f15f99081d7776432715cea2a997b32b7b3a5216f215d19c1b536c0b093100ec843fa0bd65f2101","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_8111a8278e68510b909d7476ec8571c4dc2f124b1b04f48aed108749dffee3e8"}}