{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NCGV6TNO7OGFWI3SHHX6OHTNVV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1f238591c5d73665e34190433ee543cc8d0e7a595a92ee042004776bf82c62d0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T00:06:55Z","title_canon_sha256":"9d2677995bb6b40359c4047ff47b78baaec8d961dfcbfceea9105992fa7575a8"},"schema_version":"1.0","source":{"id":"2501.18062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18062","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18062v1","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18062","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"NCGV6TNO7OGF","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"NCGV6TNO7OGFWI3S","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"NCGV6TNO","created_at":"2026-07-05T10:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:ada852a10d93461fd1bad86f3def4b16185b5ebd8229ba4ef17100b03a5432eb","target":"graph","created_at":"2026-07-05T10:07:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.18062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Carlos Georgescu, Danny Tang, Spencer Mateega","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T00:06:55Z","title":"FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18062","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4fe6718791d5a615133572b39bcc224f0e185e903d2f937a1414af8d88fd81bf","target":"record","created_at":"2026-07-05T10:07:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1f238591c5d73665e34190433ee543cc8d0e7a595a92ee042004776bf82c62d0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T00:06:55Z","title_canon_sha256":"9d2677995bb6b40359c4047ff47b78baaec8d961dfcbfceea9105992fa7575a8"},"schema_version":"1.0","source":{"id":"2501.18062","kind":"arxiv","version":1}},"canonical_sha256":"688d5f4daefb8c5b237239efe71e6dad55c51bfdc7f57d3509c5eeb7fbc8016c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"688d5f4daefb8c5b237239efe71e6dad55c51bfdc7f57d3509c5eeb7fbc8016c","first_computed_at":"2026-07-05T10:07:06.437917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:06.437917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5+yvUvGje/vjvEZ4HUel38fln193RIRoUMDmJt/R3D8XP30k0+IXUZ+cZph7u1O9Vxq+iiH0IDvtf9n71BVAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:06.438391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fe6718791d5a615133572b39bcc224f0e185e903d2f937a1414af8d88fd81bf","sha256:ada852a10d93461fd1bad86f3def4b16185b5ebd8229ba4ef17100b03a5432eb"],"state_sha256":"5354a016ff2c873637909ff872e9800dbc8d01809b45c356f70d2dd74c86fdaf"}