{"_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_7d99c30437a4aa4b8936cdb0d02e010ad362ce058e431c8b3d651fe110d54216","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_7d99c30437a4aa4b8936cdb0d02e010ad362ce058e431c8b3d651fe110d54216","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"34639a8b4ed6c6c80e50b64a06e52c6eaa5ffcf72753af6cf80872ab50af9d13","published":"Tue, 12 May 2026 00:00:00 -0400","receipt_hash":"34639a8b4ed6c6c80e50b64a06e52c6eaa5ffcf72753af6cf80872ab50af9d13","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":"34639a8b4ed6c6c80e50b64a06e52c6eaa5ffcf72753af6cf80872ab50af9d13","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:2605.10448v1 Announce Type: new \nAbstract: Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run succeeded. For example, a benchmark task may ask whether Alice's shipping address was changed, while the outcome check only verifies that the agent clicked \"Save.\" This does not guarantee that the intended state change occurred, since the agent may have modified the wrong record. Treating such a run as successful therefore makes the reported score misleading. Benchmark quality thus depends not only on task design, but also on the reliability of outcome detection.\n  We address this problem by introducing an outcome evidence reporting layer for existing benchmarks, without modifying their tasks, agents, or evaluators. The layer performs three functions. First, before scoring, it specifies which stored artifa","title":"Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation","url":"https://arxiv.org/abs/2605.10448","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.10448v1 Announce Type: new \nAbstract: Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run succeeded. For example, a benchmark task may ask whether Alice's shipping address was changed, while the outcome check only verifies that the agent clicked \"Save.\" This does not guarantee that the intended state change occurred, since the agent may have modified the wrong record. Treating such a run as successful therefore makes the reported score misleading. Benchmark quality thus depends not only on task design, but also on the reliability of outcome detection.\n  We address this problem by introducing an outcome evidence reporting layer for existing benchmarks, without modifying their tasks, agents, or evaluators. The layer performs three functions. First, before scoring, it specifies which stored artifa","title":"Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation","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/2605.10448"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a231699f217ac52f8bab493d03b248bd5d887fa82d692f6fcc04e033fe36f008843480e72ba905665aaf993f2ce00897dee296059e7c34b0fbd3c2e4a067a40e","signer":"crovia.substrate","subject":{"observed_at":"2026-05-12T04:43:42Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.10448"},"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":"3f0e79520d8be29b773f4e0ce46f16d4f729f0354bd43cc88eddbddca5442cc0","leaf_index":128409,"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":"00304b662ec4fbb1b2ec98b62a2f396b16e004971c934e0026c066111dfdbb93","side":"left"},{"sibling":"1c464b580269b541d44f2b496fe6ff8a8640ae899a904d25257911698aefb381","side":"right"},{"sibling":"ce1280bb9c95b48c1a477f70bddc903c9cd9e84ff9404ecbb1d78588d3e65625","side":"right"},{"sibling":"c48fca561abe273f86702399ac673a72354f274d1f940dd3b653324787f490e7","side":"left"},{"sibling":"0d728fddd7ee383ee1acd01cd5258c321767e1a446fb84460ed591905a9cd8ab","side":"left"},{"sibling":"1e76569690aeb5370536438a4bfc114293525ce17ebff00b5334781803f05b1b","side":"right"},{"sibling":"0d2e2a03cbbaaaf9b359ac04d26d1134ca661c8a9f351c4874b0b3550f597903","side":"right"},{"sibling":"0fac4565968e7e49cfc1d10e28cfc4966c72b4dd0deb14bce20d28acb7a0d65a","side":"left"},{"sibling":"aa3ddc60ad25fcdd4bf93520d8baeca26d807789d80fb0deffbb19c4f8882286","side":"left"},{"sibling":"077005bbaed7b42537914de0b512ed52d33243215eab288181aba807d37bf04e","side":"right"},{"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_7d99c30437a4aa4b8936cdb0d02e010ad362ce058e431c8b3d651fe110d54216"}}