{"_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_b8020fa4ef0f146a04d749a7bf9c3c8f27caeaefd55703217fea0483afdd58ce","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_b8020fa4ef0f146a04d749a7bf9c3c8f27caeaefd55703217fea0483afdd58ce","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"844769cec85b42e13e7c638a5ac3599789c965ff7cc43a1f7800d78feef3109e","published":"Wed, 08 Jul 2026 00:00:00 -0400","receipt_hash":"844769cec85b42e13e7c638a5ac3599789c965ff7cc43a1f7800d78feef3109e","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":"844769cec85b42e13e7c638a5ac3599789c965ff7cc43a1f7800d78feef3109e","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:2606.24245v3 Announce Type: replace-cross \nAbstract: Large language model (LLM) agents increasingly automate complex tasks by integrating language models with external tools and environments. However, their autonomy poses significant safety risks: agents may execute destructive commands, leak sensitive data, or violate domain constraints. Existing safety approaches face a fundamental tradeoff: hand-crafted rules are interpretable but brittle, with overly conservative rules blocking safe operations (high false positives) while permissive rules miss unsafe behaviors (high false negatives). Neural classifiers lack the interpretability required for safety-critical deployments.\n  We present AutoSpec, a framework that automatically evolves deployed expert-designed safety rules from user safe/unsafe annotations through counterexample-guided inductive synthesis (CEGIS) guided by inductive logic programming (ILP). Starting from the expert rules and a stream of annotated traces, AutoSpec i","title":"AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming","url":"https://arxiv.org/abs/2606.24245","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.24245v3 Announce Type: replace-cross \nAbstract: Large language model (LLM) agents increasingly automate complex tasks by integrating language models with external tools and environments. However, their autonomy poses significant safety risks: agents may execute destructive commands, leak sensitive data, or violate domain constraints. Existing safety approaches face a fundamental tradeoff: hand-crafted rules are interpretable but brittle, with overly conservative rules blocking safe operations (high false positives) while permissive rules miss unsafe behaviors (high false negatives). Neural classifiers lack the interpretability required for safety-critical deployments.\n  We present AutoSpec, a framework that automatically evolves deployed expert-designed safety rules from user safe/unsafe annotations through counterexample-guided inductive synthesis (CEGIS) guided by inductive logic programming (ILP). Starting from the expert rules and a stream of annotated traces, AutoSpec i","title":"AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming","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/2606.24245"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a5503acae7429a3008ee892953926df96710534933d51dcd269c8bd0df6ce66b2717fed4bfeb85b9494fee54426160a2943e9e386a43ddc6523d1a2c4e807f06","signer":"crovia.substrate","subject":{"observed_at":"2026-07-08T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.24245"},"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":"0f5d10cd1fc1e1feac78f01d85694db530cc6d33e0f5cdd929e9dac72ad2267f","leaf_index":292867,"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":"fb6c4ea5857d03ccf6799f0e177f5048454539195b6d466c80a1b63ea0235dc9","side":"left"},{"sibling":"a50a568f3fd2b08bb0e61dcba9f6e73578b6b4648b75d3fbd41a2f0ddaf10524","side":"left"},{"sibling":"9f9db90d9f17e34e76288f991feb67373f542bdf8e6b896dcda968d9aff7f250","side":"right"},{"sibling":"6e22da9d2b3ed4c118dc957d6ba6c87baff0060e684cc4e2a8e4fb5d913a9e29","side":"right"},{"sibling":"fd11fef6169f56ee2d6436f0bc84b7687a3ca1d6aaf8e58ed64ef59b146eee2d","side":"right"},{"sibling":"9ad64c6e4e0b96e008a7023c5b53a49734815b1b1a1b16378dcf9d804f9c413c","side":"right"},{"sibling":"617e77750d7be8d258b9672f3c2eda5e4b605f07228adb8c241e1d828792a13e","side":"right"},{"sibling":"a1c7308f551daa63b64ec77cc13d449bf33e99901d0dda2db2f31bbffc489f6c","side":"right"},{"sibling":"db7425c634a173a48b66583ee32c1bbc8bd9d8222fc9a058769c375b58d4e350","side":"right"},{"sibling":"734e0b99d24020d46ff89b3a21d7fd47637f7587e4afe586fb6fe1f49fb14951","side":"right"},{"sibling":"1174a91ffd715fef4004c103054ba3979b0df671a97b9986f26c644b22f7b68e","side":"right"},{"sibling":"03a737b0f0acc6f32fb2a629212bfae02d124a0d6546cc82e3c7ae458b43fda6","side":"left"},{"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_b8020fa4ef0f146a04d749a7bf9c3c8f27caeaefd55703217fea0483afdd58ce"}}