{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UZI26C55OWFRWRST6TEJR5SGJ2","short_pith_number":"pith:UZI26C55","schema_version":"1.0","canonical_sha256":"a651af0bbd758b1b4653f4c898f6464e929147f90d9f1909166c05985961250a","source":{"kind":"arxiv","id":"2109.00122","version":3},"attestation_state":"computed","paper":{"title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Routledge, Charese Smiley, Dylan Langdon, Iana Borova, Matt Beane, Reema Moussa, Sameena Shah, Ting-Hao Huang, Wenhu Chen, William Yang Wang, Zhiyu Chen","submitted_at":"2021-09-01T00:08:14Z","abstract_excerpt":"The sheer volume of financial statements makes it difficult for humans to access and analyze a business's financials. Robust numerical reasoning likewise faces unique challenges in this domain. In this work, we focus on answering deep questions over financial data, aiming to automate the analysis of a large corpus of financial documents. In contrast to existing tasks on general domain, the finance domain includes complex numerical reasoning and understanding of heterogeneous representations. To facilitate analytical progress, we propose a new large-scale dataset, FinQA, with Question-Answering"},"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":"2109.00122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-01T00:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"eddf6013526eff413653dafac9e6881b4f504c578515d49c816c155bcecab045","abstract_canon_sha256":"ee0730e185dc29ff591713147b2d7ea385ff9be0c0df930a9a4ebccba564aa6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:05.509685Z","signature_b64":"O4+eU9UCeVzddNQ4FaL93JxFeHV48YiHghrpr7xp9Uss2DqaLkfNWv9WHQgx5xxFgdp+9ly1SdxQl2RuDHopDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a651af0bbd758b1b4653f4c898f6464e929147f90d9f1909166c05985961250a","last_reissued_at":"2026-07-05T04:21:05.509169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:05.509169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Routledge, Charese Smiley, Dylan Langdon, Iana Borova, Matt Beane, Reema Moussa, Sameena Shah, Ting-Hao Huang, Wenhu Chen, William Yang Wang, Zhiyu Chen","submitted_at":"2021-09-01T00:08:14Z","abstract_excerpt":"The sheer volume of financial statements makes it difficult for humans to access and analyze a business's financials. Robust numerical reasoning likewise faces unique challenges in this domain. In this work, we focus on answering deep questions over financial data, aiming to automate the analysis of a large corpus of financial documents. In contrast to existing tasks on general domain, the finance domain includes complex numerical reasoning and understanding of heterogeneous representations. To facilitate analytical progress, we propose a new large-scale dataset, FinQA, with Question-Answering"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00122","kind":"arxiv","version":3},"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/2109.00122/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":"2109.00122","created_at":"2026-07-05T04:21:05.509229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.00122v3","created_at":"2026-07-05T04:21:05.509229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00122","created_at":"2026-07-05T04:21:05.509229+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZI26C55OWFR","created_at":"2026-07-05T04:21:05.509229+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZI26C55OWFRWRST","created_at":"2026-07-05T04:21:05.509229+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZI26C55","created_at":"2026-07-05T04:21:05.509229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19887","citing_title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14355","citing_title":"Herculean: An Agentic Benchmark for Financial Intelligence","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15482","citing_title":"FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08886","citing_title":"FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15482","citing_title":"FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21495","citing_title":"Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20273","citing_title":"ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12047","citing_title":"Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10718","citing_title":"SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2","json":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2.json","graph_json":"https://pith.science/api/pith-number/UZI26C55OWFRWRST6TEJR5SGJ2/graph.json","events_json":"https://pith.science/api/pith-number/UZI26C55OWFRWRST6TEJR5SGJ2/events.json","paper":"https://pith.science/paper/UZI26C55"},"agent_actions":{"view_html":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2","download_json":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2.json","view_paper":"https://pith.science/paper/UZI26C55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.00122&json=true","fetch_graph":"https://pith.science/api/pith-number/UZI26C55OWFRWRST6TEJR5SGJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/UZI26C55OWFRWRST6TEJR5SGJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2/action/storage_attestation","attest_author":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2/action/author_attestation","sign_citation":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2/action/citation_signature","submit_replication":"https://pith.science/pith/UZI26C55OWFRWRST6TEJR5SGJ2/action/replication_record"}},"created_at":"2026-07-05T04:21:05.509229+00:00","updated_at":"2026-07-05T04:21:05.509229+00:00"}