{"_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_596a2412163e841f1597cda7bf115c7d7a1d28792b819675bbe9360fadf92638","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_596a2412163e841f1597cda7bf115c7d7a1d28792b819675bbe9360fadf92638","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"68a2bae820edfe2cbca69ee25a61e600bc19fff98b3eedb9ad0f632019d8a1b4","published":"Fri, 03 Jul 2026 00:00:00 -0400","receipt_hash":"68a2bae820edfe2cbca69ee25a61e600bc19fff98b3eedb9ad0f632019d8a1b4","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":"68a2bae820edfe2cbca69ee25a61e600bc19fff98b3eedb9ad0f632019d8a1b4","observed_at":"2026-07-03T04:43:38.241623Z","parent_run_hash":"f0e30469786257a5e74170498cacb4c028623bf32d6d06d4dbadc488960545be","published":"Fri, 03 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:2607.01740v1 Announce Type: new \nAbstract: Public LLM leaderboards optimise for global average performance and do not capture the specific cognitive demands of financial-services work: a model that leads on MMLU-Pro may underperform on document-grounded compliance reasoning, and a coding leader may handle multi-turn customer interactions poorly. We present a meta-benchmarking framework that organises 452 publicly reported benchmarks into 41 O*NET Generalized Work Activities and aggregates those into 38 BIAN banking business domains spanning sales, operations, risk, and support work. A multiplicative weighting scheme (discrimination x coverage x recency), computed over a rolling model window, rewards benchmarks that still separate the best models, are widely reported, and remain in active use, suppressing saturated legacy tests automatically. These weights scale the K-factor in a pairwise Elo tournament, producing cross-benchmark-comparable work-activity scores without raw score n","title":"Meta-Benchmarks for Financial-Services LLM Evaluation","url":"https://arxiv.org/abs/2607.01740","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.01740v1 Announce Type: new \nAbstract: Public LLM leaderboards optimise for global average performance and do not capture the specific cognitive demands of financial-services work: a model that leads on MMLU-Pro may underperform on document-grounded compliance reasoning, and a coding leader may handle multi-turn customer interactions poorly. We present a meta-benchmarking framework that organises 452 publicly reported benchmarks into 41 O*NET Generalized Work Activities and aggregates those into 38 BIAN banking business domains spanning sales, operations, risk, and support work. A multiplicative weighting scheme (discrimination x coverage x recency), computed over a rolling model window, rewards benchmarks that still separate the best models, are widely reported, and remain in active use, suppressing saturated legacy tests automatically. These weights scale the K-factor in a pairwise Elo tournament, producing cross-benchmark-comparable work-activity scores without raw score n","title":"Meta-Benchmarks for Financial-Services LLM Evaluation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-03T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.01740"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:d467e45ce82834676a2f521c80d501bb3370630fcfd3045f00fe1c11a7c10d0e230b7acdb315ba0e78d6db43251d9364e000411bc6cba46b1d954d6fbc103306","signer":"crovia.substrate","subject":{"observed_at":"2026-07-03T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.01740"},"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":"14d169b9f304770c514a9365d29def487766fb46c942355fab202ac929035136","leaf_index":275366,"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":"da83ea8ab4679178740dfb660235e0a09e07146f3996f66b0b5b19eaa7601af8","side":"right"},{"sibling":"12a6f4cbb1ba9dba5d2dea123ba39dd58692afd9409f2228470ebd76b8138f72","side":"left"},{"sibling":"fc43f3e6178135d19c48571704e4506951ddd4ff678118372324fb9aceac4dbc","side":"left"},{"sibling":"a0f5360bbd197c18eb20caf2c6608edb0af36810a4e8c065b3eb02e469dfdb66","side":"right"},{"sibling":"d72aa1f925dab408f8a7feb7ee9f4fcbb7643a503e99fe6c7bef38ec0e25984f","side":"right"},{"sibling":"1031e5965521cd2d57d0a685e70068eda5d4e9645dbb1aca1d0133d801ecf1e2","side":"left"},{"sibling":"90e9fb2a20374342836f11695e291756a1f8a0197a80f5da7958594a976dd668","side":"right"},{"sibling":"fd055e725b36f5bebbaeb18583f9d7011c4d8c2a608a11cbd2c166cd895e7a85","side":"left"},{"sibling":"e1a65581e9d68211aa8ba0d138c8d2a4e80afd551e6d1b00c4575c39085df705","side":"left"},{"sibling":"92c062f377cd53076b8dfe55c25ab217059e20113433673cc5747b9348b07e01","side":"left"},{"sibling":"e36f7633c67452f41a7377a7bec9b2d454442688d26539321eebf92cae9db0f0","side":"right"},{"sibling":"4dbd8247ba08a5432c7d6540711da9acb2f59e6189865aa8552dee37f69286a9","side":"right"},{"sibling":"41cd1885dc3fcb51e49eeb887d6d22ec2cfa58df0e4f8d7c7dddf3a1b0ce8249","side":"left"},{"sibling":"8a09562f6b247c1c3cd1fea36cb3b8f1cf5c575479dd514573856a380a964bf5","side":"left"},{"sibling":"723981908169653ca6d835aa9b8381a8c7ad3e3e3830d0792bc32032cda615ee","side":"right"},{"sibling":"c0594fa1ee81d5f019cccc7b5e51af603c6d7e43995498c451012060c7d06165","side":"right"},{"sibling":"4de6a2fb22efbb50c84dc62abeb0f2cbc8c663a9540aeba9e758ebfdfe3e86dd","side":"right"},{"sibling":"fdbb3519f8dc411a4043dfb5abdbfea5441e130326183ac2247c42584033f152","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":275799,"merkle_root":"2581d0d6e5fa345cdf2e8ab3b191ace76d6b14189901ab0e4c2291ca1d1ae1e6","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260703T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-03T05:38:09Z","sig_algorithm":"ed25519","signature":"e44a386a5ae00c0e7fc67b1179bb9060bf0fefc006e454fec70e27668182ff497d1e2faf0c3b22de0917beefb7c80e880dae925a3f67e1b16aa0eb44bf947407","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_596a2412163e841f1597cda7bf115c7d7a1d28792b819675bbe9360fadf92638"}}