{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4JYHGMDGCH3TI6ES3NPU5RSJZZ","short_pith_number":"pith:4JYHGMDG","schema_version":"1.0","canonical_sha256":"e27073306611f7347892db5f4ec649ce748c0f6588d95702535d521627af4c7b","source":{"kind":"arxiv","id":"2607.01740","version":1},"attestation_state":"computed","paper":{"title":"Meta-Benchmarks for Financial-Services LLM Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Blair Hudson","submitted_at":"2026-07-02T05:52:32Z","abstract_excerpt":"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 c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.01740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T05:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"9856b53f7b69f72e90d8132fb16a0e5a15c43404e43bb1d841d92c57068e9e6c","abstract_canon_sha256":"174055cc09f88124728aa88979bae5b2fe3b808c80a45fc5fe417dcc847ef322"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:28.252104Z","signature_b64":"PY5OFxN0vl1FLp4tSU1V0xib8LqCOMFy83A+TPzolERKCZvQOSHxqKFS20V2m+YR+4Bx+f9awMu4QiWQg/e5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e27073306611f7347892db5f4ec649ce748c0f6588d95702535d521627af4c7b","last_reissued_at":"2026-07-03T01:17:28.251680Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:28.251680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Benchmarks for Financial-Services LLM Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Blair Hudson","submitted_at":"2026-07-02T05:52:32Z","abstract_excerpt":"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 c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01740","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.01740/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.01740","created_at":"2026-07-03T01:17:28.251750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01740v1","created_at":"2026-07-03T01:17:28.251750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01740","created_at":"2026-07-03T01:17:28.251750+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JYHGMDGCH3T","created_at":"2026-07-03T01:17:28.251750+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JYHGMDGCH3TI6ES","created_at":"2026-07-03T01:17:28.251750+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JYHGMDG","created_at":"2026-07-03T01:17:28.251750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ","json":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ.json","graph_json":"https://pith.science/api/pith-number/4JYHGMDGCH3TI6ES3NPU5RSJZZ/graph.json","events_json":"https://pith.science/api/pith-number/4JYHGMDGCH3TI6ES3NPU5RSJZZ/events.json","paper":"https://pith.science/paper/4JYHGMDG"},"agent_actions":{"view_html":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ","download_json":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ.json","view_paper":"https://pith.science/paper/4JYHGMDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01740&json=true","fetch_graph":"https://pith.science/api/pith-number/4JYHGMDGCH3TI6ES3NPU5RSJZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4JYHGMDGCH3TI6ES3NPU5RSJZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ/action/storage_attestation","attest_author":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ/action/author_attestation","sign_citation":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ/action/citation_signature","submit_replication":"https://pith.science/pith/4JYHGMDGCH3TI6ES3NPU5RSJZZ/action/replication_record"}},"created_at":"2026-07-03T01:17:28.251750+00:00","updated_at":"2026-07-03T01:17:28.251750+00:00"}