{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JGK7I3YMDCHLRUBVYFAISMU2YW","short_pith_number":"pith:JGK7I3YM","schema_version":"1.0","canonical_sha256":"4995f46f0c188eb8d035c14089329ac59d5ae74001ac24eb6d38d189ab7f5b59","source":{"kind":"arxiv","id":"2401.02982","version":4},"attestation_state":"computed","paper":{"title":"FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Chenghao Jia, Chong Yang, Jie Zhou, Man Lan, Qingquan Wu, Shangqing Zhao, Shu Liu, Xinlin Zhuang, Zhaoguang Long","submitted_at":"2024-01-01T15:26:23Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. However, their proficiency and reliability in the specialized domain of financial data analysis, particularly focusing on data-driven thinking, remain uncertain. To bridge this gap, we introduce \\texttt{FinDABench}, a comprehensive benchmark designed to evaluate the financial data analysis capabilities of LLMs within this context. \\texttt{FinDABench} assesses LLMs across three dimensions: 1) \\textbf{Foundational Ability}, evaluating the models' ability to perform financial numerical calculation"},"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":"2401.02982","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T15:26:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5778339f7e95052903c714e53f1e22e65ba1c2956d665c965f103d3a53843ff","abstract_canon_sha256":"602d87d438de43eda349c54f1705d06159eb027c2a70636473b703aca1fdecb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:46.284180Z","signature_b64":"6R/E1O1snFC9gtumHTn7oVsqT6Fw1qFEDEAXIm4MjQ3VyszWB6D+UMAhNxJDlhyw8wS2F4cobN0LE7iZ7D86BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4995f46f0c188eb8d035c14089329ac59d5ae74001ac24eb6d38d189ab7f5b59","last_reissued_at":"2026-07-05T08:31:46.283686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:46.283686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Chenghao Jia, Chong Yang, Jie Zhou, Man Lan, Qingquan Wu, Shangqing Zhao, Shu Liu, Xinlin Zhuang, Zhaoguang Long","submitted_at":"2024-01-01T15:26:23Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. However, their proficiency and reliability in the specialized domain of financial data analysis, particularly focusing on data-driven thinking, remain uncertain. To bridge this gap, we introduce \\texttt{FinDABench}, a comprehensive benchmark designed to evaluate the financial data analysis capabilities of LLMs within this context. \\texttt{FinDABench} assesses LLMs across three dimensions: 1) \\textbf{Foundational Ability}, evaluating the models' ability to perform financial numerical calculation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02982","kind":"arxiv","version":4},"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/2401.02982/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":"2401.02982","created_at":"2026-07-05T08:31:46.283742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02982v4","created_at":"2026-07-05T08:31:46.283742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02982","created_at":"2026-07-05T08:31:46.283742+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGK7I3YMDCHL","created_at":"2026-07-05T08:31:46.283742+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGK7I3YMDCHLRUBV","created_at":"2026-07-05T08:31:46.283742+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGK7I3YM","created_at":"2026-07-05T08:31:46.283742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00051","citing_title":"Business Utility of Large Language Models as Exploratory Data Analysis Agents","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW","json":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW.json","graph_json":"https://pith.science/api/pith-number/JGK7I3YMDCHLRUBVYFAISMU2YW/graph.json","events_json":"https://pith.science/api/pith-number/JGK7I3YMDCHLRUBVYFAISMU2YW/events.json","paper":"https://pith.science/paper/JGK7I3YM"},"agent_actions":{"view_html":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW","download_json":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW.json","view_paper":"https://pith.science/paper/JGK7I3YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02982&json=true","fetch_graph":"https://pith.science/api/pith-number/JGK7I3YMDCHLRUBVYFAISMU2YW/graph.json","fetch_events":"https://pith.science/api/pith-number/JGK7I3YMDCHLRUBVYFAISMU2YW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW/action/storage_attestation","attest_author":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW/action/author_attestation","sign_citation":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW/action/citation_signature","submit_replication":"https://pith.science/pith/JGK7I3YMDCHLRUBVYFAISMU2YW/action/replication_record"}},"created_at":"2026-07-05T08:31:46.283742+00:00","updated_at":"2026-07-05T08:31:46.283742+00:00"}