{"_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_af4d069d940c78f1c3a3dbd2aa191b4b2acfb600286aa8c45c5f9faefd768616","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_af4d069d940c78f1c3a3dbd2aa191b4b2acfb600286aa8c45c5f9faefd768616","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b51385b43261fba289239955b02dab4ff3dd06dbb2b7ef2a7cba16afb5a0df07","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"b51385b43261fba289239955b02dab4ff3dd06dbb2b7ef2a7cba16afb5a0df07","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":"b51385b43261fba289239955b02dab4ff3dd06dbb2b7ef2a7cba16afb5a0df07","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 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:2605.26937v1 Announce Type: cross \nAbstract: Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood. Existing knowledge benchmarks typically rely on predefined questions (e.g., \"What is the birth date of M.L. King?\"), evaluating only knowledge that benchmark designers explicitly choose to query, a problematic availability bias.\n  In this paper, we introduce open knowledge evaluation, a new paradigm for LLM knowledge benchmarking. Instead of asking narrow questions, it evaluates models on the knowledge they choose to surface in response to open-ended elicitation prompts (e.g., \"Tell me everything you know about M.L. King\"). This shifts the focus from predefined answer retrieval toward characterizing the knowledge models naturally express.\n  We instantiate this paradigm with BeQu (Beyond Questions), a benchmark of 10,000 entities paired with reference corpora for statement verification. Using BeQu, we evaluate a broad r","title":"Beyond Questions: Evaluating What Large Language Models (Actually) Know","url":"https://arxiv.org/abs/2605.26937","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.26937v1 Announce Type: cross \nAbstract: Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood. Existing knowledge benchmarks typically rely on predefined questions (e.g., \"What is the birth date of M.L. King?\"), evaluating only knowledge that benchmark designers explicitly choose to query, a problematic availability bias.\n  In this paper, we introduce open knowledge evaluation, a new paradigm for LLM knowledge benchmarking. Instead of asking narrow questions, it evaluates models on the knowledge they choose to surface in response to open-ended elicitation prompts (e.g., \"Tell me everything you know about M.L. King\"). This shifts the focus from predefined answer retrieval toward characterizing the knowledge models naturally express.\n  We instantiate this paradigm with BeQu (Beyond Questions), a benchmark of 10,000 entities paired with reference corpora for statement verification. Using BeQu, we evaluate a broad r","title":"Beyond Questions: Evaluating What Large Language Models (Actually) Know","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.26937"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ba136480a5c83a0e580628d3eee7c97a3ce7a4fbfb1f119fcef3689af5b3aedb899c6c155a199f673c386d6510dfb50d0d4a6617c4537d87b4ea4994f3c62406","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.26937"},"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":"dcde872c188ba4a8d8a4e640685fe0ca13e1a9875c26efc8e8fa4479a12a26e2","leaf_index":153762,"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":"4c83ee45db5e3399a019b14315a1750ff2395c300ba923e32f9c167090bd9b91","side":"right"},{"sibling":"92e97b5c8c2d60aa91a814da9171b76a84253a80d2c882074ead74ce045cff13","side":"left"},{"sibling":"ee8dc0bbfe4452eef4454655afd0a9b76ffc0d5f75e653f7c6301047b9bdec79","side":"right"},{"sibling":"45b5330d501931b23f0e84d7e5a9cc05dfd7e8e3f334cb569d9e710e5ba2424f","side":"right"},{"sibling":"8c1e54f60787011017fd4a70d3e76f2a4ea1926c6be9b3de9a6ce9dbc5d5e876","side":"right"},{"sibling":"095987b193de9546d4c6b56d77d24978a978ecb6b93d0a339243886796ca8167","side":"left"},{"sibling":"1471bf5749919a9fc3bde5501a5be14605bb1a8f59a38e7c49e3fd6fa081da33","side":"right"},{"sibling":"dd15059d2d503b45e928c26e84bea4e5b2d187abeace390e61efd18d39e80f21","side":"left"},{"sibling":"c56e46802f42ead6bcf79619c80428b6dc22e9afc9611a87f0d04a5ef9acadd7","side":"right"},{"sibling":"3165125427a29042fc9d02858a59a68858dbdcb2e19d1afa5f6dd6a95cfbce6a","side":"right"},{"sibling":"04b9a68b8ec6fa37251564383c685c23ce69e5e031df4eae69f79a3a334b68bf","side":"right"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","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":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","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_af4d069d940c78f1c3a3dbd2aa191b4b2acfb600286aa8c45c5f9faefd768616"}}