{"_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_2b814cf1163abc85a35cdab1e424fe304424e8bd499cbaf1538d9bebde3514c3","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_2b814cf1163abc85a35cdab1e424fe304424e8bd499cbaf1538d9bebde3514c3","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a9f1bef2fc763efe831501c61faec7e9a641dc02e12161654d2b53346f9b7826","published":"Wed, 01 Jul 2026 00:00:00 -0400","receipt_hash":"a9f1bef2fc763efe831501c61faec7e9a641dc02e12161654d2b53346f9b7826","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":"a9f1bef2fc763efe831501c61faec7e9a641dc02e12161654d2b53346f9b7826","observed_at":"2026-07-01T04:43:38.812993Z","parent_run_hash":"0e10ec7d671a375a4e18d8645653df2b4352c82fe16fae2a400af6f7634d6699","published":"Wed, 01 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:2605.11030v2 Announce Type: replace-cross \nAbstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims. We present an executable benchmarking suite that makes these objects explicit under a shared evidence-admission contract. The suite connects WebArena Verified, a SWE-Gym slice with SWE-bench-compatible verification, and MiniWoB++ through common workload adapters, task manifests, event schemas, replay/freeze policy, declared drivers, and reporting pipelines. In the canonical release, the gate separates paper-facing evidence from preflight, fixture, smoke, and diagnostic rows while preserving non-admitted artifacts for audit and onboarding. The admitted evidence records latency, invalid-action behavior, patch-generation cost, verifier metadata, replay bindings, and provenance under one auditable","title":"An Executable Benchmarking Suite for Tool-Using Agents","url":"https://arxiv.org/abs/2605.11030","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.11030v2 Announce Type: replace-cross \nAbstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims. We present an executable benchmarking suite that makes these objects explicit under a shared evidence-admission contract. The suite connects WebArena Verified, a SWE-Gym slice with SWE-bench-compatible verification, and MiniWoB++ through common workload adapters, task manifests, event schemas, replay/freeze policy, declared drivers, and reporting pipelines. In the canonical release, the gate separates paper-facing evidence from preflight, fixture, smoke, and diagnostic rows while preserving non-admitted artifacts for audit and onboarding. The admitted evidence records latency, invalid-action behavior, patch-generation cost, verifier metadata, replay bindings, and provenance under one auditable","title":"An Executable Benchmarking Suite for Tool-Using Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-01T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.11030"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:22728cb57146022df90f45448d0dd4244b29de51dc32e8cbffb94017eeb995ca0c01a8259b32102b265ff97c34e42ecab04a8d811bcdd8f6d785be44cf5d8803","signer":"crovia.substrate","subject":{"observed_at":"2026-07-01T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.11030"},"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":"fd31d55f1dfba84bdbb992baa942e791b09726a8459796c4df7410fce9131f0f","leaf_index":268719,"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":"a2e9a9f7a3637484b3f25b71027590592e44b136d927b2a0aa140405d1dc87c0","side":"left"},{"sibling":"88488811b6120107614d69dc849933e44ea3fa8ce6e90a39b6c341804e493f94","side":"left"},{"sibling":"2d33cf590382a7c66df7cbf5a5eea59eef45c5787f301458835f26898847345d","side":"left"},{"sibling":"42d16bad4f7c2800e3e3accea93b27a8ad5a1a8d02585cbc8b1f9af8ca3e2d98","side":"left"},{"sibling":"d9b873370c92e4dc69826859ea55f9515cd72414e290a0e766255ee3ffed8394","side":"right"},{"sibling":"7a1f969ec5b4bf9f076acec001dab3c248a82031e6ffe639dc95059da328f9e9","side":"left"},{"sibling":"4b40722a8676aba99a1cededb6270927be9c50d0f94c30aa826fa53a7a32b4a6","side":"right"},{"sibling":"58c3799598a549d54786b91e80a9c8daea4edcb3c27437b6b16ccadf6dc2889e","side":"left"},{"sibling":"4b14e8ccae46b588748944ffaf410222f66cebc2ac58d936cbe16847b7be9508","side":"left"},{"sibling":"bbd9a20451913e8c7b910f616d5661d9b281a94af70d201ba50b3112d429521b","side":"right"},{"sibling":"85af80e45748c1e0da1e2f42d9d66da8996016888a034f20eb17ff0a73b69eab","side":"right"},{"sibling":"4575fde969d1d9a2984cc01a37ac8441238f74527d42874272dc5582dadebb4f","side":"left"},{"sibling":"f536de281672cbf0b583a3dc46faef1de2823b72bd9265c7b60e889131cc268d","side":"left"},{"sibling":"95b8b0f67237052a17c41fa8cbdce2b79bcb5aeeba3fdb239d4c4497e598115d","side":"right"},{"sibling":"c2f351f771cee329448890504d9436792ba482e50250ca9a19289311131f96c8","side":"right"},{"sibling":"c39bfb2e911ca37ae997690bfc04128ae32e6806ee1cb3908781a7e6685022a0","side":"right"},{"sibling":"a101b4c60ef6854ac3d750eef02d8e2e06c153284b5ecb7111302f97eb129797","side":"right"},{"sibling":"eae2a3de5cb35455ad60125e196cfadaba8a590c53146e95028469f53f70349c","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":268860,"merkle_root":"d098f25810d0569730b6c0e170d57f329a70359d483b47874b5f2fc51d23de65","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260701T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-01T05:38:05Z","sig_algorithm":"ed25519","signature":"64f37f0e3df0556baa55b924a736cab8005643fa0ab65b503f22407de30eab293e6e0bd62904270fda38d05084bb350c8c0d0aadb2c5a6bae5f1c54598e6d30c","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_2b814cf1163abc85a35cdab1e424fe304424e8bd499cbaf1538d9bebde3514c3"}}