{"_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_aff8d4aa8f2489ae3d27db31a48ed964a3abab86bd4f04480658b021ae2058a2","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_aff8d4aa8f2489ae3d27db31a48ed964a3abab86bd4f04480658b021ae2058a2","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a8d5fad5910a7fd4c62d583fd726e9cfd3df5e7ed8ffb535dafd261299ecc8fd","published":"Tue, 30 Jun 2026 00:00:00 -0400","receipt_hash":"a8d5fad5910a7fd4c62d583fd726e9cfd3df5e7ed8ffb535dafd261299ecc8fd","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":"a8d5fad5910a7fd4c62d583fd726e9cfd3df5e7ed8ffb535dafd261299ecc8fd","observed_at":"2026-06-30T04:43:04.087680Z","parent_run_hash":"74f7ab392cc702044101fe24a76a2fdad11164cd79ce725aad6c446a477e89c5","published":"Tue, 30 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:2606.29887v1 Announce Type: new \nAbstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies. In this work, we study this setting under the paradigm of in-context policy guardrailing, where guardrails predict safety violations based on policy specifications provided in context. To systematically evaluate this capability, we introduce SafePyramid, a safety benchmark comprising 1,000 multi-turn conversations across 10 domains and 3,000 corresponding application-specific policies, which together contain 61,699 distinct natural-language rules. SafePyramid organizes the evaluation into three difficulty levels: L0 evaluates individual-rule understanding, L1 evaluates reasoning over rule dependencies, and L2 evaluates adaptation of full novel policy frameworks defined in context. To ensure benchmark quality, we employ a rigorous multi-st","title":"SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing","url":"https://arxiv.org/abs/2606.29887","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.29887v1 Announce Type: new \nAbstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies. In this work, we study this setting under the paradigm of in-context policy guardrailing, where guardrails predict safety violations based on policy specifications provided in context. To systematically evaluate this capability, we introduce SafePyramid, a safety benchmark comprising 1,000 multi-turn conversations across 10 domains and 3,000 corresponding application-specific policies, which together contain 61,699 distinct natural-language rules. SafePyramid organizes the evaluation into three difficulty levels: L0 evaluates individual-rule understanding, L1 evaluates reasoning over rule dependencies, and L2 evaluates adaptation of full novel policy frameworks defined in context. To ensure benchmark quality, we employ a rigorous multi-st","title":"SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-30T04:43:04Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.29887"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:30baad215dc97fb2e0a7d27ee0d12e12c7ab1a1d2c2f90b87c0070f9bc7bf1b013fa8b01ef3aefddc2b9215dc3e0f6e6a35ba10466f13ef9e35f89427654690e","signer":"crovia.substrate","subject":{"observed_at":"2026-06-30T04:43:04Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.29887"},"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":"8310f8247c6ec9424856aa2bdf3811044cfb42daa7bf7cc24185f34e63948b96","leaf_index":264670,"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":"7f620a4404208504ea8bdedf8ac381436fbf1a06fae36aa90042b7a031951f6f","side":"right"},{"sibling":"5e5b8f80580502647bd93812fc9fc6a44f216f0e18851a5e9a6e4f29555cd979","side":"left"},{"sibling":"45d11539c5c14867bdbbda0dc3db76253534a8acd094adcc651baf8f5dcc1e35","side":"left"},{"sibling":"5fb886dda05f89b83420240d448332df82569997ee2f2f1ea886d8161e7fdaca","side":"left"},{"sibling":"bf5abbece4c47e777840eea282973f8d3523bd1268a61bde40cfc9c6c81a4469","side":"left"},{"sibling":"0a27664369302f0956d74b2834cdf1f3aec65e09110e09edfc2d796fc639a390","side":"right"},{"sibling":"47460e4ad3c750350537b3d1cfaa7edcd6bdd9654e146d3d3828bac68075ac72","side":"left"},{"sibling":"0adb33f90b5325f1bcd6d9d08abc79306f0275cec357b6a5d5a9aeb8dae006eb","side":"left"},{"sibling":"a18aac5bf38684ad71f816483beee037e0b60af41587ea19ba92b263e2076d3e","side":"left"},{"sibling":"e814db3b1e34c91aa2d674ee041f8e093e00869024c9f6f8c4d72cab70c3a87e","side":"right"},{"sibling":"23994bf0974e5c9c7f63a61b4f0a48b0ca756a4adc34a8f85f878e774c37dfbe","side":"right"},{"sibling":"f9b4bed84fa6990c71ad2887c91bda183001f05f6b648f21d1273045a26b11fd","side":"left"},{"sibling":"173d2dc4b29ee04ea41d6d0ebc334c4bc2d46e7ee4230c94765413f24fb4bc42","side":"right"},{"sibling":"112461f7c0ec411116fb5c6c90fe95cea9d8f188b9fe08afe25a837ac02d0071","side":"right"},{"sibling":"ea9488204352c49db8f7daf05eefcd7628ecf9413830346674801a99d0654a94","side":"right"},{"sibling":"6261c13b9922cb657f10d1e5d36ec15d8771cf8766e36c61dcbffb7bed57e396","side":"right"},{"sibling":"fa19aa3faf287618b820bcfceebb366152ad521dd20ef9f51e977816663e448b","side":"right"},{"sibling":"c32f943406b62d1fc59b7f7e243492174c8e1caba8c8a2705f86c773315736e0","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":265374,"merkle_root":"9636001ecab173cb6af10dc7c71eb14585daa62f9c0a6f027046f05633156891","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260630T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-30T05:38:03Z","sig_algorithm":"ed25519","signature":"6d4b8fd9b9da856cbb5fba7540877c6a63fa18a5ec3eaf28dc4d6d1c64921c9c0565f8c95f4b7aec0e7744fd7754844f051baf863db708cad768765b416a7b0c","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_aff8d4aa8f2489ae3d27db31a48ed964a3abab86bd4f04480658b021ae2058a2"}}