{"_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_9b3575982dfadc9173ff03f35cfca9059477a18d178dfb7d6bfe952480f75522","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_9b3575982dfadc9173ff03f35cfca9059477a18d178dfb7d6bfe952480f75522","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"88378cccb67ca6591a8c3039217828a1586adbf7ef212b515f5228861c829ce9","published":"Wed, 10 Jun 2026 00:00:00 -0400","receipt_hash":"88378cccb67ca6591a8c3039217828a1586adbf7ef212b515f5228861c829ce9","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":"88378cccb67ca6591a8c3039217828a1586adbf7ef212b515f5228861c829ce9","observed_at":"2026-06-10T04:43:37.461885Z","parent_run_hash":"23aff1a6f676ba7ca33f70f4ddfae1dd282fb86104d577ce9be510d81a94c5dc","published":"Wed, 10 Jun 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:2606.11166v1 Announce Type: cross \nAbstract: Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are primarily based on how LLMs perform on benchmarking tasks that measure average performance across standardized datasets. Primary limitations of many benchmarking tasks are that they often measure performance based on content directly included in LLM training data, and they frequently do not assess the reliability of LLM performance or the magnitude of LLM errors. However, in high stakes contexts, these qualities are critically important. Through a novel LLM benchmarking task that requires writing computer code to complete a data analysis task, we compare the performance of a frontier LLM against submissions from human experts and explicitly measure the variance of responses and the magnitude of errors. Our study reveals that the human experts perform better on average on a range of metrics and","title":"Flaws in the LLM Automation Narrative","url":"https://arxiv.org/abs/2606.11166","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.11166v1 Announce Type: cross \nAbstract: Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are primarily based on how LLMs perform on benchmarking tasks that measure average performance across standardized datasets. Primary limitations of many benchmarking tasks are that they often measure performance based on content directly included in LLM training data, and they frequently do not assess the reliability of LLM performance or the magnitude of LLM errors. However, in high stakes contexts, these qualities are critically important. Through a novel LLM benchmarking task that requires writing computer code to complete a data analysis task, we compare the performance of a frontier LLM against submissions from human experts and explicitly measure the variance of responses and the magnitude of errors. Our study reveals that the human experts perform better on average on a range of metrics and","title":"Flaws in the LLM Automation Narrative","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-10T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.11166"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:7dc2d2f96d25ef2d3aea27b171dd5d390bc196edd87e0e0b33b8fc4e32e637924de900b0de34a2702eb6570f26f12242671e523fea0e3c80ebdf742be1804f00","signer":"crovia.substrate","subject":{"observed_at":"2026-06-10T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.11166"},"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":"fcf143afdcbf0a49bcef286208497d139d1115f358073d567df38f8c910c283f","leaf_index":226120,"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":"a11a06785677757f12ab6cc18ba421fd01629e53a9c9bed17dfccfeb1d78a92a","side":"right"},{"sibling":"fdb438a7957157f50194668ada22e328bc1064363dbd8ec216fa0bed6722b23f","side":"right"},{"sibling":"83c8e85a97e6ef2e1789a43a937653c48729847a116ee50c2c59c36543f31ef3","side":"right"},{"sibling":"7f3c2e846ae8890a0685d45ec3ec6149626039373883cf0fb58bdaa8e49ad9f1","side":"left"},{"sibling":"6d61498a9373367fb4b6e32566ee2038009bcb6b611b7792a9304910ea09b9be","side":"right"},{"sibling":"2ee12d5b009abe0086e35e2ae134b79dd68d8a6bf6849547e4b0c90973f95c98","side":"right"},{"sibling":"c20ffe9501388a4e560b300f20c62c7cd1bd74b8c3502a50047853354b09279c","side":"left"},{"sibling":"670eed753a274b9b7494adeace1b88e7adfaecd7eeaa78b82e0fc83a75d20865","side":"right"},{"sibling":"b180cfc3f8638c912e90139ec42e2e3fd9b67b3fe342b36e8954314633ae5f61","side":"left"},{"sibling":"a4d17aefe58175050dc159af6246658fcf1c9f3ed57aacf1b350fc3261de4e69","side":"left"},{"sibling":"280b980aa0c7756b0b0cb22658f26466d36f0e70fbc3312cd2311d9898e30b8f","side":"right"},{"sibling":"c98954d4b658b1dda60fe52576fcf9bf21a2d49c67fb63f8c30f16ab5f721938","side":"right"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_9b3575982dfadc9173ff03f35cfca9059477a18d178dfb7d6bfe952480f75522"}}