{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YI64NYTHPZFLPBKNLRKRXTCVE","short_pith_number":"pith:3YI64NYT","schema_version":"1.0","canonical_sha256":"de11ee37133bf255bc2a6ae2a8de62a9372472fb530b27c3454f79003c6eb721","source":{"kind":"arxiv","id":"2411.19504","version":2},"attestation_state":"computed","paper":{"title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Binhang Yuan, Chen Wang, Chenyue Li, Guangxin He, You Peng, Zipeng Qiu","submitted_at":"2024-11-29T06:48:13Z","abstract_excerpt":"The advance of large language models (LLMs) has unlocked great opportunities in complex multi-modal data management tasks, particularly in question answering (QA) over complicated multi-table relational data. Despite significant progress, systematically evaluating LLMs on multi-table QA remains a critical challenge due to the inherent complexity of analyzing the modality of relational data structures and the potentially large scale of serialized tabular data. Existing benchmarks primarily focus on single-table QA, failing to capture the intricacies of connections across multiple relational tab"},"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":"2411.19504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-29T06:48:13Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"99a92ea1c51b1ff06fdd622a73937e287b22f08e1febdc4e7bfccd22a81741a1","abstract_canon_sha256":"aa20b9ddc8ed5b9035ca78419c0a2ade9f46f582582c0a7e55713d58e4cc8912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:37.691809Z","signature_b64":"QsBb0otCStyZrZiB1DV1WyBMBTWFuJq+9EIh8YHKe9ToNgxauAKLLZoPL3ZdFPYTP4UCcwGL7D9pMotlhwoDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de11ee37133bf255bc2a6ae2a8de62a9372472fb530b27c3454f79003c6eb721","last_reissued_at":"2026-06-09T01:04:37.691293Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:37.691293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Binhang Yuan, Chen Wang, Chenyue Li, Guangxin He, You Peng, Zipeng Qiu","submitted_at":"2024-11-29T06:48:13Z","abstract_excerpt":"The advance of large language models (LLMs) has unlocked great opportunities in complex multi-modal data management tasks, particularly in question answering (QA) over complicated multi-table relational data. Despite significant progress, systematically evaluating LLMs on multi-table QA remains a critical challenge due to the inherent complexity of analyzing the modality of relational data structures and the potentially large scale of serialized tabular data. Existing benchmarks primarily focus on single-table QA, failing to capture the intricacies of connections across multiple relational tab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19504","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/2411.19504/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":"2411.19504","created_at":"2026-06-09T01:04:37.691368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19504v2","created_at":"2026-06-09T01:04:37.691368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19504","created_at":"2026-06-09T01:04:37.691368+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YI64NYTHPZF","created_at":"2026-06-09T01:04:37.691368+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YI64NYTHPZFLPBK","created_at":"2026-06-09T01:04:37.691368+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YI64NYT","created_at":"2026-06-09T01:04:37.691368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.02537","citing_title":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE","json":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE.json","graph_json":"https://pith.science/api/pith-number/3YI64NYTHPZFLPBKNLRKRXTCVE/graph.json","events_json":"https://pith.science/api/pith-number/3YI64NYTHPZFLPBKNLRKRXTCVE/events.json","paper":"https://pith.science/paper/3YI64NYT"},"agent_actions":{"view_html":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE","download_json":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE.json","view_paper":"https://pith.science/paper/3YI64NYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19504&json=true","fetch_graph":"https://pith.science/api/pith-number/3YI64NYTHPZFLPBKNLRKRXTCVE/graph.json","fetch_events":"https://pith.science/api/pith-number/3YI64NYTHPZFLPBKNLRKRXTCVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE/action/storage_attestation","attest_author":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE/action/author_attestation","sign_citation":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE/action/citation_signature","submit_replication":"https://pith.science/pith/3YI64NYTHPZFLPBKNLRKRXTCVE/action/replication_record"}},"created_at":"2026-06-09T01:04:37.691368+00:00","updated_at":"2026-06-09T01:04:37.691368+00:00"}