{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NCGV6TNO7OGFWI3SHHX6OHTNVV","short_pith_number":"pith:NCGV6TNO","schema_version":"1.0","canonical_sha256":"688d5f4daefb8c5b237239efe71e6dad55c51bfdc7f57d3509c5eeb7fbc8016c","source":{"kind":"arxiv","id":"2501.18062","version":1},"attestation_state":"computed","paper":{"title":"FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Carlos Georgescu, Danny Tang, Spencer Mateega","submitted_at":"2025-01-30T00:06:55Z","abstract_excerpt":"FinanceQA is a testing suite that evaluates LLMs' performance on complex numerical financial analysis tasks that mirror real-world investment work. Despite recent advances, current LLMs fail to meet the strict accuracy requirements of financial institutions, with models failing approximately 60% of realistic tasks that mimic on-the-job analyses at hedge funds, private equity firms, investment banks, and other financial institutions. The primary challenges include hand-spreading metrics, adhering to standard accounting and corporate valuation conventions, and performing analysis under incomplet"},"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":"2501.18062","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T00:06:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9d2677995bb6b40359c4047ff47b78baaec8d961dfcbfceea9105992fa7575a8","abstract_canon_sha256":"1f238591c5d73665e34190433ee543cc8d0e7a595a92ee042004776bf82c62d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:06.438391Z","signature_b64":"u5+yvUvGje/vjvEZ4HUel38fln193RIRoUMDmJt/R3D8XP30k0+IXUZ+cZph7u1O9Vxq+iiH0IDvtf9n71BVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"688d5f4daefb8c5b237239efe71e6dad55c51bfdc7f57d3509c5eeb7fbc8016c","last_reissued_at":"2026-07-05T10:07:06.437917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:06.437917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Carlos Georgescu, Danny Tang, Spencer Mateega","submitted_at":"2025-01-30T00:06:55Z","abstract_excerpt":"FinanceQA is a testing suite that evaluates LLMs' performance on complex numerical financial analysis tasks that mirror real-world investment work. Despite recent advances, current LLMs fail to meet the strict accuracy requirements of financial institutions, with models failing approximately 60% of realistic tasks that mimic on-the-job analyses at hedge funds, private equity firms, investment banks, and other financial institutions. The primary challenges include hand-spreading metrics, adhering to standard accounting and corporate valuation conventions, and performing analysis under incomplet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18062","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/2501.18062/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":"2501.18062","created_at":"2026-07-05T10:07:06.437983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18062v1","created_at":"2026-07-05T10:07:06.437983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18062","created_at":"2026-07-05T10:07:06.437983+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCGV6TNO7OGF","created_at":"2026-07-05T10:07:06.437983+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCGV6TNO7OGFWI3S","created_at":"2026-07-05T10:07:06.437983+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCGV6TNO","created_at":"2026-07-05T10:07:06.437983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26235","citing_title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09106","citing_title":"Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06132","citing_title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17305","citing_title":"BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV","json":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV.json","graph_json":"https://pith.science/api/pith-number/NCGV6TNO7OGFWI3SHHX6OHTNVV/graph.json","events_json":"https://pith.science/api/pith-number/NCGV6TNO7OGFWI3SHHX6OHTNVV/events.json","paper":"https://pith.science/paper/NCGV6TNO"},"agent_actions":{"view_html":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV","download_json":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV.json","view_paper":"https://pith.science/paper/NCGV6TNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18062&json=true","fetch_graph":"https://pith.science/api/pith-number/NCGV6TNO7OGFWI3SHHX6OHTNVV/graph.json","fetch_events":"https://pith.science/api/pith-number/NCGV6TNO7OGFWI3SHHX6OHTNVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV/action/storage_attestation","attest_author":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV/action/author_attestation","sign_citation":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV/action/citation_signature","submit_replication":"https://pith.science/pith/NCGV6TNO7OGFWI3SHHX6OHTNVV/action/replication_record"}},"created_at":"2026-07-05T10:07:06.437983+00:00","updated_at":"2026-07-05T10:07:06.437983+00:00"}