{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YU4ATALK54QXNX2QJJNPWFRNND","short_pith_number":"pith:YU4ATALK","schema_version":"1.0","canonical_sha256":"c53809816aef2176df504a5afb162d68f2d695cc159c7a74f6b19537db55a4ab","source":{"kind":"arxiv","id":"2105.07624","version":2},"attestation_state":"computed","paper":{"title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Wang, Fengbin Zhu, Fuli Feng, Jiancheng Lv, Shuo Zhang, Tat-Seng Chua, Wenqiang Lei, Youcheng Huang","submitted_at":"2021-05-17T06:12:06Z","abstract_excerpt":"Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. We further propose a novel QA model termed TAGOP, w"},"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":"2105.07624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-17T06:12:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dce2c3b9631379f9dee0fed3cdd7876efa8a9f98801a8c9dee41182237acd83","abstract_canon_sha256":"d2260742bb61fe1888a229162ac188c6db10ccfd47a702721b32ba9c2a4e4c3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:59.250195Z","signature_b64":"BDXiLF2BSymekAuzCiu/hVXzf2/BGmL2duYtGx+u1jDIbKqtjkfPPobQfbcyMI8wXPotP3YZ1wIad67AXY6PDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c53809816aef2176df504a5afb162d68f2d695cc159c7a74f6b19537db55a4ab","last_reissued_at":"2026-07-05T02:44:59.249760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:59.249760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Wang, Fengbin Zhu, Fuli Feng, Jiancheng Lv, Shuo Zhang, Tat-Seng Chua, Wenqiang Lei, Youcheng Huang","submitted_at":"2021-05-17T06:12:06Z","abstract_excerpt":"Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. We further propose a novel QA model termed TAGOP, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07624","kind":"arxiv","version":2},"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/2105.07624/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":"2105.07624","created_at":"2026-07-05T02:44:59.249816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07624v2","created_at":"2026-07-05T02:44:59.249816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07624","created_at":"2026-07-05T02:44:59.249816+00:00"},{"alias_kind":"pith_short_12","alias_value":"YU4ATALK54QX","created_at":"2026-07-05T02:44:59.249816+00:00"},{"alias_kind":"pith_short_16","alias_value":"YU4ATALK54QXNX2Q","created_at":"2026-07-05T02:44:59.249816+00:00"},{"alias_kind":"pith_short_8","alias_value":"YU4ATALK","created_at":"2026-07-05T02:44:59.249816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02113","citing_title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30907","citing_title":"BlueFin: Benchmarking LLM Agents on Financial Spreadsheets","ref_index":34,"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":128,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29399","citing_title":"LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents","ref_index":17,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23262","citing_title":"Design and Report Benchmarks for Knowledge Work","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":124,"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":84,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08886","citing_title":"FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs","ref_index":32,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20816","citing_title":"Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20505","citing_title":"RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13415","citing_title":"Attention Grounded Enhancement for Visual Document Retrieval","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13330","citing_title":"FIND: Toward Multimodal Financial Reasoning and Question Answering for Indic Languages","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08146","citing_title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":61,"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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":61,"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":2,"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":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11970","citing_title":"INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND","json":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND.json","graph_json":"https://pith.science/api/pith-number/YU4ATALK54QXNX2QJJNPWFRNND/graph.json","events_json":"https://pith.science/api/pith-number/YU4ATALK54QXNX2QJJNPWFRNND/events.json","paper":"https://pith.science/paper/YU4ATALK"},"agent_actions":{"view_html":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND","download_json":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND.json","view_paper":"https://pith.science/paper/YU4ATALK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07624&json=true","fetch_graph":"https://pith.science/api/pith-number/YU4ATALK54QXNX2QJJNPWFRNND/graph.json","fetch_events":"https://pith.science/api/pith-number/YU4ATALK54QXNX2QJJNPWFRNND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND/action/storage_attestation","attest_author":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND/action/author_attestation","sign_citation":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND/action/citation_signature","submit_replication":"https://pith.science/pith/YU4ATALK54QXNX2QJJNPWFRNND/action/replication_record"}},"created_at":"2026-07-05T02:44:59.249816+00:00","updated_at":"2026-07-05T02:44:59.249816+00:00"}