{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HUXWTDDQLAZU3Z7TAMAZMKZJRL","short_pith_number":"pith:HUXWTDDQ","schema_version":"1.0","canonical_sha256":"3d2f698c7058334de7f30301962b298ad07a279205bf3b8fc79ab156124b6bb5","source":{"kind":"arxiv","id":"2408.09174","version":2},"attestation_state":"computed","paper":{"title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daixin Shu, Di Liang, Ge Zhang, Guanglin Niu, Jiaheng Liu, Jian Yang, Linzheng Chai, Tianzhen Sun, Tongliang Li, Xianfu Cheng, Xianjie Wu, Xinrun Du, Zhoujun Li","submitted_at":"2024-08-17T11:40:10Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have markedly enhanced the interpretation and processing of tabular data, introducing previously unimaginable capabilities. Despite these achievements, LLMs still encounter significant challenges when applied in industrial scenarios, particularly due to the increased complexity of reasoning required with real-world tabular data, underscoring a notable disparity between academic benchmarks and practical applications. To address this discrepancy, we conduct a detailed investigation into the application of tabular data in industrial scenarios an"},"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":"2408.09174","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-17T11:40:10Z","cross_cats_sorted":[],"title_canon_sha256":"626c8526ce454d9e09655a2bfb49f898592395dae0285db722b2de295dd65b08","abstract_canon_sha256":"20ed5049677d8590e5f633e80c51e6c109dce1b8c276682c4fb65bed9fc87b03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:36.379189Z","signature_b64":"pU9VzMVpqy6BlHvMMEqS7Vab/zXBrA4Tm4A3Re7uDmIWEetYWq4w1C6zRIBv5WjyzCk9YAook2iCtjvciltcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2f698c7058334de7f30301962b298ad07a279205bf3b8fc79ab156124b6bb5","last_reissued_at":"2026-07-05T10:33:36.378348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:36.378348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daixin Shu, Di Liang, Ge Zhang, Guanglin Niu, Jiaheng Liu, Jian Yang, Linzheng Chai, Tianzhen Sun, Tongliang Li, Xianfu Cheng, Xianjie Wu, Xinrun Du, Zhoujun Li","submitted_at":"2024-08-17T11:40:10Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have markedly enhanced the interpretation and processing of tabular data, introducing previously unimaginable capabilities. Despite these achievements, LLMs still encounter significant challenges when applied in industrial scenarios, particularly due to the increased complexity of reasoning required with real-world tabular data, underscoring a notable disparity between academic benchmarks and practical applications. To address this discrepancy, we conduct a detailed investigation into the application of tabular data in industrial scenarios an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09174","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/2408.09174/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":"2408.09174","created_at":"2026-07-05T10:33:36.378453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09174v2","created_at":"2026-07-05T10:33:36.378453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09174","created_at":"2026-07-05T10:33:36.378453+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUXWTDDQLAZU","created_at":"2026-07-05T10:33:36.378453+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUXWTDDQLAZU3Z7T","created_at":"2026-07-05T10:33:36.378453+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUXWTDDQ","created_at":"2026-07-05T10:33:36.378453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03660","citing_title":"TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01495","citing_title":"FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17051","citing_title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL","json":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL.json","graph_json":"https://pith.science/api/pith-number/HUXWTDDQLAZU3Z7TAMAZMKZJRL/graph.json","events_json":"https://pith.science/api/pith-number/HUXWTDDQLAZU3Z7TAMAZMKZJRL/events.json","paper":"https://pith.science/paper/HUXWTDDQ"},"agent_actions":{"view_html":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL","download_json":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL.json","view_paper":"https://pith.science/paper/HUXWTDDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09174&json=true","fetch_graph":"https://pith.science/api/pith-number/HUXWTDDQLAZU3Z7TAMAZMKZJRL/graph.json","fetch_events":"https://pith.science/api/pith-number/HUXWTDDQLAZU3Z7TAMAZMKZJRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL/action/storage_attestation","attest_author":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL/action/author_attestation","sign_citation":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL/action/citation_signature","submit_replication":"https://pith.science/pith/HUXWTDDQLAZU3Z7TAMAZMKZJRL/action/replication_record"}},"created_at":"2026-07-05T10:33:36.378453+00:00","updated_at":"2026-07-05T10:33:36.378453+00:00"}