{"_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_fe5ee6673975066fe5282059067126ecb5aaf8bb72dcf1bb7a73470be4a51012","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_fe5ee6673975066fe5282059067126ecb5aaf8bb72dcf1bb7a73470be4a51012","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"15014381479fcf41d5cd908323a04b7cb3fc917d2d95c6a6557bcb81b0224b2f","published":"Fri, 17 Jul 2026 00:00:00 -0400","receipt_hash":"15014381479fcf41d5cd908323a04b7cb3fc917d2d95c6a6557bcb81b0224b2f","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":"15014381479fcf41d5cd908323a04b7cb3fc917d2d95c6a6557bcb81b0224b2f","observed_at":"2026-07-17T04:43:38.280949Z","parent_run_hash":"113193614a8af99887180226d4e28a8b71d957da5fe3694f0e7a56807c145504","published":"Fri, 17 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:2607.13705v2 Announce Type: replace \nAbstract: As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable a","title":"AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities","url":"https://arxiv.org/abs/2607.13705","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.13705v2 Announce Type: replace \nAbstract: As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable a","title":"AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-17T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.13705"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e04ea3c8ab373611868a89ec835acf1f7f86fe4e602e667242f4890d2f4e99cb50a1636c5f9cd32ed8aa96b69dbfdb5842b10c4bea99d22e47e4aa7157e73e02","signer":"crovia.substrate","subject":{"observed_at":"2026-07-17T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.13705"},"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":"6ddb9a5379ed806eb5290514c7c29ef1c0167bfb22bec165e7d81d507a92c149","leaf_index":323207,"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":"4412e9104d4baea90216e0565871ef0466b1a7939a0484b1df14958a4b703544","side":"left"},{"sibling":"c6a0db32816f82356b511be5df1e029a3de776408a99e66c976353bb5ff74730","side":"left"},{"sibling":"30fc0588af9603af038a0a1030e9399bf34c7b822cd6e34a007eea558b35c240","side":"left"},{"sibling":"a996a1f358447f5727a3a12ad1bef90501d17cd0ef576f6e4f2a8a0a4ab41435","side":"right"},{"sibling":"2beab7d1097b80f5ad01cbeec08ed9a58db70c31ac4a5e613a053b5841072cb5","side":"right"},{"sibling":"d6805227f449f6a32787d356287cf7316d84ebabb2924195b6333b6278eda03a","side":"right"},{"sibling":"aebfde2196fc7fd2178375305cab7b77eaaa1ebf74063760b1eb4e14f8814e82","side":"right"},{"sibling":"b5089ad323e3a111201fbe7e6c412f67ceaa2ae3f4a343adb22b037ec4c30755","side":"left"},{"sibling":"4242cc570ec8c36a37f3f6f20dcae20b49fccc17c7b53ba47d8715e465bec585","side":"right"},{"sibling":"be025f48721bfc0ca7107f0454bda3ab460e50539f0caeb1bf839a8dabcf036c","side":"left"},{"sibling":"05a09763743cdc09fc45cf454e4e3ea4a0d1cd74f9c8162b2a57e2c873160908","side":"left"},{"sibling":"de3120ef2488b8a791a686b47257da4e612256abdfcdda7519265e7edd47d041","side":"left"},{"sibling":"e86f56a4883492da5b5e7b0201324c52946e865e69b99ebb532f41fe3c658ee4","side":"right"},{"sibling":"34d85f6ad6cc7dfa79d90e2b9ff99a561bcdc75b0301bbbd3e83861f54535c1e","side":"left"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"9b11714124b9b951ff9450b0ee9d625a0b70b6da2cf388bd3df1475eec0b17ba","side":"right"},{"sibling":"a4523a9014d45df43e006e9210a73428c380d771f2c650a1b986910759b0cdf7","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":323382,"merkle_root":"2f4d32419c80a9600aba5a480fc3fb7012ec0a695c91a1b055048e78760b65ca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260717T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-17T05:38:31Z","sig_algorithm":"ed25519","signature":"495308c7bf004117807331d3f71d0b079f6bd7ed7737faa58c773b1b3e80ee84928d2d8519cc7d2b809506501aada1be6546f72c7ecda3dad5445cbb44502209","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_fe5ee6673975066fe5282059067126ecb5aaf8bb72dcf1bb7a73470be4a51012"}}