{"_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_d458ed14340d52e8528cc0562b7fd1de6b8cc057773b639b642b20b8de3c3b43","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_d458ed14340d52e8528cc0562b7fd1de6b8cc057773b639b642b20b8de3c3b43","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fde6b7c98955261ab0944a6098dcd04959e5b979f1b24cc0516813636beddceb","published":"Mon, 11 May 2026 00:00:00 -0400","receipt_hash":"fde6b7c98955261ab0944a6098dcd04959e5b979f1b24cc0516813636beddceb","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":"fde6b7c98955261ab0944a6098dcd04959e5b979f1b24cc0516813636beddceb","observed_at":"2026-05-11T04:43:50.688999Z","parent_run_hash":"8244cc3d66edb4604be5ded19e92c0b47893b228a258432a9c53a5796a870982","published":"Mon, 11 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:2510.19788v4 Announce Type: replace \nAbstract: World models are central to building AI agents capable of flexible reasoning and planning. Yet current evaluations (i) test only properties measurable from observed interactions, such as next-frame prediction or task return, and (ii) do not test whether a learned model supports diverse queries about the environment. In contrast, humans build $\\textit{general-purpose}$ models that can answer many different questions about an environment$\\unicode{x2014}$including questions that require understanding global structure and counterfactual consequences.\n  We propose $\\textit{WorldTest}$: a protocol for evaluating whether agents learn models that support multiple $\\textit{environment-level queries}\\unicode{x2014}$questions whose answers depend on properties of the full environment, not just observed trajectories. Individually, these queries can target properties (e.g., reachability or the effects of interventions) that no single rollout dist","title":"Benchmarking World-Model Learning with Environment-Level Queries","url":"https://arxiv.org/abs/2510.19788","vendor":"arxiv_cs_ai"},"summary":"arXiv:2510.19788v4 Announce Type: replace \nAbstract: World models are central to building AI agents capable of flexible reasoning and planning. Yet current evaluations (i) test only properties measurable from observed interactions, such as next-frame prediction or task return, and (ii) do not test whether a learned model supports diverse queries about the environment. In contrast, humans build $\\textit{general-purpose}$ models that can answer many different questions about an environment$\\unicode{x2014}$including questions that require understanding global structure and counterfactual consequences.\n  We propose $\\textit{WorldTest}$: a protocol for evaluating whether agents learn models that support multiple $\\textit{environment-level queries}\\unicode{x2014}$questions whose answers depend on properties of the full environment, not just observed trajectories. Individually, these queries can target properties (e.g., reachability or the effects of interventions) that no single rollout dist","title":"Benchmarking World-Model Learning with Environment-Level Queries","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-11T04:43:50Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2510.19788"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:71de90641509c40abc96ad8bcc0220fd9b367b32469c4fe62731f539a0235b4ce84c1855c4f5134a6afdbc210b3be4ed17fad72a454b305285d35fe3b83ef00c","signer":"crovia.substrate","subject":{"observed_at":"2026-05-11T04:43:50Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2510.19788"},"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":"3dc1f8d72e0d78ade069f7fd4217e03f83b27345ea4d18570da34a3b31808dd6","leaf_index":126572,"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":"5106943a86be67af39ded36190acbefb59f07799159ce8ba1401bd75177f2a75","side":"right"},{"sibling":"ccddd167228f5847425bc32d81bf89f7db24b864cbf129e7adb577c8804be611","side":"right"},{"sibling":"bd4c2f3f25be7a8c2ccafb4b40b4d79112e2c8c530bf758b2e26945b0dc8e1d7","side":"left"},{"sibling":"5959e7f727e5860e7754fb2d65d5ebcd92a18de447387590f639a179e1d4d02f","side":"left"},{"sibling":"43e0203ee7f52df7227eea88f9fefe490f28b9da29f2207160f5c80d8dabe1bd","side":"right"},{"sibling":"0a7c27e63de07c97e9f4dde994f7c411af7bc2f3593ebb6cbf0b31cdbe89b83b","side":"left"},{"sibling":"29f7475758dbfba222e92bceb258f532f323f301f5980a2e877cfa3325400dd7","side":"left"},{"sibling":"ad7b1a4dca274f08be7bc11dcd03ffbe41ba3906e71a39530ef457984a3802ed","side":"right"},{"sibling":"62d48549e4d4466089a57a96bd9bea15741d62a7cb314f0f9c37c4c22ac650fa","side":"right"},{"sibling":"a2c696699a233359c7b4b418ebd356db453d4b886f4bd076ef34b15ee86144a3","side":"left"},{"sibling":"1a581be91236d1f25e8d47fe5efa0e2b51b7f0f6d706ef76a9093067688e5d56","side":"left"},{"sibling":"878cc30108509c9fa1fc52705a216f519d73b647916fcbdfc30a389934d3364b","side":"left"},{"sibling":"ae7dfff36ba07d9f48c36c28a341482ef244ee13cd0efd49aee2bbef2fd65f87","side":"right"},{"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_d458ed14340d52e8528cc0562b7fd1de6b8cc057773b639b642b20b8de3c3b43"}}