{"_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_62f25f5c15c99dea17d25d4b03cca7a8e9f06d28d89a6e0b786454d76cec46ed","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_62f25f5c15c99dea17d25d4b03cca7a8e9f06d28d89a6e0b786454d76cec46ed","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"79e90ff88e7edab9abbf596c5e42bbd83e4e88219607f8700d75bc480ef8f86c","published":"Tue, 12 May 2026 00:00:00 -0400","receipt_hash":"79e90ff88e7edab9abbf596c5e42bbd83e4e88219607f8700d75bc480ef8f86c","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":"79e90ff88e7edab9abbf596c5e42bbd83e4e88219607f8700d75bc480ef8f86c","observed_at":"2026-05-12T04:43:42.564879Z","parent_run_hash":"4cc5aca0c1b8116c9ab92405e0260204f01cf7ce2e49dea9d7e123236f5dc13b","published":"Tue, 12 May 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:2512.20798v5 Announce Type: replace \nAbstract: As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of explicitly harmful instructions or completion of complex multi-step tasks. However, there is a lack of benchmarks designed to capture emergent outcome-driven constraint violations, which arise when agents pursue goal optimization under strong performance incentives while deprioritizing ethical, legal, or safety constraints. To address this gap, we introduce a benchmark of 40 scenarios in production-inspired sandbox environments. Each scenario requires multi-step actions, and the agent's performance is tied to a specific Key Performance Indicator (KPI). Each scenario features Mandated (direct KPI-outcome mandate) and Incentivized (KPI-pressure-driven) variations to distinguish failures under direct ","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","url":"https://arxiv.org/abs/2512.20798","vendor":"arxiv_cs_ai"},"summary":"arXiv:2512.20798v5 Announce Type: replace \nAbstract: As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of explicitly harmful instructions or completion of complex multi-step tasks. However, there is a lack of benchmarks designed to capture emergent outcome-driven constraint violations, which arise when agents pursue goal optimization under strong performance incentives while deprioritizing ethical, legal, or safety constraints. To address this gap, we introduce a benchmark of 40 scenarios in production-inspired sandbox environments. Each scenario requires multi-step actions, and the agent's performance is tied to a specific Key Performance Indicator (KPI). Each scenario features Mandated (direct KPI-outcome mandate) and Incentivized (KPI-pressure-driven) variations to distinguish failures under direct ","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-12T04:43:42Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2512.20798"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:fb68560866cc4dc3d960ccc845bb25bde8bc8e674731d19d8defb78bf7d47c5ef3e8ce9609b26fbdca68a3b0c2ff4ac1f0e4a70e611edf2c47855555273f9500","signer":"crovia.substrate","subject":{"observed_at":"2026-05-12T04:43:42Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2512.20798"},"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":"8f5c4634a3c5863d70a85107675c91e053b22fb9fcb33b16b5a98cedc68b9ff9","leaf_index":128956,"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":"a6a988d6917ed7f08a3a5fbf936f140cf760d41926a320a78cdb5cfd0a7eac0d","side":"right"},{"sibling":"344debb92298b3bbd4d0e9793eeb89b7d10618c2fea18c5c861b22de72362040","side":"right"},{"sibling":"5459081d9c569696337830db203b7a0f73391462ccbc6bdffcce780435f00c66","side":"left"},{"sibling":"7f5820f0791efb07a35ecac9b9818207b992ea29e55b170ba64bcf83a7156504","side":"left"},{"sibling":"a5597533fcfa4dfb6989bdd529e3714603d1750a4ce472077b5eee3aac0ce298","side":"left"},{"sibling":"6aec6c64a8c51acafa3cd6f2510901a65685bb88a027ca6990ac432e2978b856","side":"left"},{"sibling":"c76bba0c216c73590d44e9b2dbdda205cb4803404f532bfebb832fe2ca20fafe","side":"right"},{"sibling":"5eb042446399e2602ae7dd8d9f9f2cac58abf22ff48527ae02c589594da10510","side":"left"},{"sibling":"9b7895252355a8c8a373671590682bbf4d36d41befce49b5e889eaf896415156","side":"left"},{"sibling":"1d74b0fb79eace68949b4d82b0e430b1d9eb122c125f67f5be7d50c074c228e7","side":"left"},{"sibling":"c6eaf7a4fcab2db96e9e9423acb6922c80f64882d0f3f50d09e53a4807d23084","side":"left"},{"sibling":"df12eaabc0a370aff5d0488478f48d2b3f90d025c903643f98ea804b017688ec","side":"right"},{"sibling":"ffc4d51379293bc3e1910c7d612f409dc610fd9acf8241793fb89f82e1bad4ef","side":"left"},{"sibling":"62ac6554017807bd83187f5a3e5f4f72d6c482616429c2780e9fff1f4845fa04","side":"left"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_62f25f5c15c99dea17d25d4b03cca7a8e9f06d28d89a6e0b786454d76cec46ed"}}