{"_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_8953b22eab6ebf82712fc927e23021176a0d61f353c6a41c129d67982ae1ae7e","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_8953b22eab6ebf82712fc927e23021176a0d61f353c6a41c129d67982ae1ae7e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"2906aeb300a4889126f1fac658c78ca8cc3a548cd91b7eed988f11694544b8d2","published":"Fri, 29 May 2026 00:00:00 -0400","receipt_hash":"2906aeb300a4889126f1fac658c78ca8cc3a548cd91b7eed988f11694544b8d2","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":"2906aeb300a4889126f1fac658c78ca8cc3a548cd91b7eed988f11694544b8d2","observed_at":"2026-05-29T04:43:58.478092Z","parent_run_hash":"0fcd87efcfe67ccb9952f747541debc16793919a4d20fd71ca0ad5516a0a13ee","published":"Fri, 29 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:2605.29253v1 Announce Type: new \nAbstract: Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task-oracle outcomes with structured process evidence. FullTax converts the aligned trajectories into structured anomaly supervision: binary labels, supporting evidence, onset/span localization, severity, recoverability, and a 5-class anomaly taxonomy. Using OpenClawBench, we make the Outcome-Process Gap measurable. Among 31,135 oracle-passing execution","title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories","url":"https://arxiv.org/abs/2605.29253","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.29253v1 Announce Type: new \nAbstract: Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task-oracle outcomes with structured process evidence. FullTax converts the aligned trajectories into structured anomaly supervision: binary labels, supporting evidence, onset/span localization, severity, recoverability, and a 5-class anomaly taxonomy. Using OpenClawBench, we make the Outcome-Process Gap measurable. Among 31,135 oracle-passing execution","title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-29T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.29253"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:46a469e13c5071183b1e314c3c334f3130948ca4a4c23c62961256bd44a36b7b800072328a296ea41491c70cf84b3c4efd988b748ccde010ef1b1947762a7c05","signer":"crovia.substrate","subject":{"observed_at":"2026-05-29T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.29253"},"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":"3bdecaa934582b8f1bb836efa59b02c48dda497de8fe9cf61575c12f1b114fef","leaf_index":157678,"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":"86f733277a744faa25c8c70722989a473427affc46749cc38c5615b4af9a35e1","side":"right"},{"sibling":"2d9aad031fcbfdae5d4b2ef01c5d84e9641703a99dbba7617cc122cebbb7120b","side":"left"},{"sibling":"673d500718399b4f14a83ce6c86e5767fa5528ba24126ed1e010c875f6c667ad","side":"left"},{"sibling":"1400968afc0d5d44dbf5445f9d1a54ae49d7a0a770024bd094dc20a4ceef0265","side":"left"},{"sibling":"1dec423965f2bf69ef076bd5035cd732f74f244143f86714cbbf14699621b04a","side":"right"},{"sibling":"1eead04ebe1be8d8dddce54b72650927fcf3982f00346da13e29805b59a5f05a","side":"left"},{"sibling":"f65c4257e1e3e5a8d1432a336a21d8e806501313e0c2888ff215dba80f4c4cfe","side":"left"},{"sibling":"27e5f392a568b11659ecd5aed52502b5e6d88eea7862dffac806a2d7b5a9ef78","side":"left"},{"sibling":"ece7b043912367e6be374d77e09128de032af83a2b87e39b397350dd279ebe83","side":"left"},{"sibling":"39ec45a73732c5ed1abe96972bd3bc32a517083704467dde1c8117578609124d","side":"left"},{"sibling":"68b4895a8015cdde1c1baeaf63a8382cf574ce4d2ad88d596d4217ce2238245e","side":"left"},{"sibling":"0bc831354843fa27f7ba6a4b3080a72fd440b9a76d1bac63429adfbfe6549bca","side":"right"},{"sibling":"995b421824624a8282c7f44e64c64ee35344800f477ae1845b41be14d3fab94c","side":"right"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"eef0e8906a749d3470f89beeedc723f37a5737010bbb0dcc7cf91515338e5a3e","side":"right"},{"sibling":"1a07e481a9407d71aad078ce854cdeee362163c887fe10f889b0ecf0b5e749ad","side":"right"},{"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":158251,"merkle_root":"485e6b31fe60c8beba5b394808c7e4c32448b2ff65c2482c480ca0e2a2eda718","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260529T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-29T05:37:37Z","sig_algorithm":"ed25519","signature":"bbf9f005201182fce4f9d94c7a9d01a508b56daf7d9611bd73514f5f616bc059d0e5e1f2edfc95716e6fe08ef5fae38b558cbf7f2fd8f9d5dfe4c34a54c83005","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_8953b22eab6ebf82712fc927e23021176a0d61f353c6a41c129d67982ae1ae7e"}}