{"_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_ab190ddc4b11df229152c97628967f7da686afbef332773378a948596efa424a","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_ab190ddc4b11df229152c97628967f7da686afbef332773378a948596efa424a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"5eabebc8f61083fecc40a78237f28faf493fb1d3acaa0de9361a74e84cbe79b0","published":"Mon, 20 Jul 2026 00:00:00 -0400","receipt_hash":"5eabebc8f61083fecc40a78237f28faf493fb1d3acaa0de9361a74e84cbe79b0","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":"5eabebc8f61083fecc40a78237f28faf493fb1d3acaa0de9361a74e84cbe79b0","observed_at":"2026-07-20T04:43:09.641409Z","parent_run_hash":"0fd83663f0f57da59b26313ca1a35283a3e9f06e3165d3e143d26f7174743aca","published":"Mon, 20 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:2607.15263v2 Announce Type: replace-cross \nAbstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 investigation challenges. Instead of reporting only best-case success, we compare models at fixed cost levels and decompose performance by inference spend and tool spend. Our results show distinct scalingregimes for red- and blue-team tasks. Offensive CTF performance improves with additional test-time compute, and scaled open-weight models can approach frontier proprietary systems while remaining cost-competitive. Defensive SOC investigati","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents","url":"https://arxiv.org/abs/2607.15263","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.15263v2 Announce Type: replace-cross \nAbstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 investigation challenges. Instead of reporting only best-case success, we compare models at fixed cost levels and decompose performance by inference spend and tool spend. Our results show distinct scalingregimes for red- and blue-team tasks. Offensive CTF performance improves with additional test-time compute, and scaled open-weight models can approach frontier proprietary systems while remaining cost-competitive. Defensive SOC investigati","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-20T04:43:09Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.15263"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:85336b67e0bc80c3f49a2b0e622a3c0e61659160ecf56a6b4cb4b7c22d3b0996f998b728cccc423dbc10f4ca659aaced23d9aed430fc64af1043b1c1e33d520b","signer":"crovia.substrate","subject":{"observed_at":"2026-07-20T04:43:09Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.15263"},"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":"79c73aab2e2f647a384a047dae995fcd723f6b4dfedcc1bcb23e8bb87f49051e","leaf_index":333427,"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":"0a403cd42400601a83cf2465571f473f4bbdfb380eb4dad4bbb18b879905a8b8","side":"left"},{"sibling":"1b0bf069c7ec88df9a62d5f5cad0063653dfbc2a45b41c42ac31f48f57fa200d","side":"left"},{"sibling":"fb6a91d219a643512172f6f8e87825f724a21c33fa9f7235821f1cfecb4b59d4","side":"right"},{"sibling":"8dbd65055db44143eeda3bdcf7c71baaa4c21478b6d42bd35739c4644101e204","side":"right"},{"sibling":"c2b5de42179645ed6a897d9c9187da12665c677c2c57f24aea987b3c4d05317c","side":"left"},{"sibling":"3b19ff326ff94316abce15d4a489cecf2bb3d15919d216452b61575e48c0fef3","side":"left"},{"sibling":"fd7a2f2e44dc3f058d65e59ceb20b3d20eb68b3d8d84208ea601209a4c4df8a9","side":"left"},{"sibling":"5f23b1a0a67d8fa1aa690680510620f249f8d6683d46c202fca306510fbe398e","side":"right"},{"sibling":"f720760992870795e6d2b913ad9162f9e144b821ea97e4dada744d0cac06e93b","side":"right"},{"sibling":"45c0e4431502711514503abd48e8b3d34ee2f4bffa994c883aaf2adecd0ad8e9","side":"left"},{"sibling":"dedd2da92d9447ddf1b1db68fe20109a426ed18359861ed746907ac820021a8d","side":"left"},{"sibling":"a1c43cc7cd9c775fac33940ee5124aece01596733f003fc53743f43483f9f597","side":"right"},{"sibling":"b5ad3eafd7eeb74c063261356fdd9bf6059ee6d0bf1e3c70e60731b394a5536e","side":"left"},{"sibling":"93e399d152203db688c6a5a58d25131205603504f5b79123a1f2b5a5ed9c1e54","side":"right"},{"sibling":"b6e0cad7f6eb9107f0edd276f1a9942635d8cd6d60d2a97e7daac08b110dc209","side":"right"},{"sibling":"80ec062e7e625dc3f9bb5865cb5198696bbec2608e48abae5670677b90695899","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"0aced6f0c9dec3e6cc9e89b68b70f5f8ce7e1eb13606d92db1917b76e57393c7","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":333540,"merkle_root":"ee60f62b8a724dd9bde638d638caf32cefec4440f832018b457ff47a0ec56a8c","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260720T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-20T05:38:36Z","sig_algorithm":"ed25519","signature":"82a3787e628bfab19c377d875220e1aaedfc498736c545f4708a1b887e8398afdf306995994493a36c864ff7139a2d436b905ce7081aaa540789aa4f707dc800","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_ab190ddc4b11df229152c97628967f7da686afbef332773378a948596efa424a"}}