{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5PQZ2C6VXQMIGOYLQLFSUPBZWY","short_pith_number":"pith:5PQZ2C6V","schema_version":"1.0","canonical_sha256":"ebe19d0bd5bc18833b0b82cb2a3c39b61df8595b8f07c1a600238fb26aa46476","source":{"kind":"arxiv","id":"2305.12820","version":2},"attestation_state":"computed","paper":{"title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Yates, Evangelos Kanoulas, Maarten de Rijke, Vaishali Pal","submitted_at":"2023-05-22T08:25:15Z","abstract_excerpt":"Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over multiple tables in a relational database or web page. Single table questions do not involve common table operations such as set operations, Cartesian products (joins), or nested queries. Furthermore, multi-table operations often result in a tabular output, which necessitates table generation capabilities of tabular QA models. To fill this gap, we propose a new task of answerin"},"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":"2305.12820","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T08:25:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e062459fc5b28ce75e28bf3c6439273a3de7f1917b0d7b94fd2b47bbbde2976f","abstract_canon_sha256":"df5bb9079798f61787d378912550a24a6136f8553c7d4a6ce1350e60dcbb9408"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:57.734421Z","signature_b64":"b8/yrVMF10ikGkdX+1t3tsaulLoMj6Paf9Aowh3hhIEbznQmeVT0fg1FNKayyJ8aq3CAADugusat+BQnts2yAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebe19d0bd5bc18833b0b82cb2a3c39b61df8595b8f07c1a600238fb26aa46476","last_reissued_at":"2026-07-05T06:38:57.733948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:57.733948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Yates, Evangelos Kanoulas, Maarten de Rijke, Vaishali Pal","submitted_at":"2023-05-22T08:25:15Z","abstract_excerpt":"Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over multiple tables in a relational database or web page. Single table questions do not involve common table operations such as set operations, Cartesian products (joins), or nested queries. Furthermore, multi-table operations often result in a tabular output, which necessitates table generation capabilities of tabular QA models. To fill this gap, we propose a new task of answerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12820","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/2305.12820/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":"2305.12820","created_at":"2026-07-05T06:38:57.734002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12820v2","created_at":"2026-07-05T06:38:57.734002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12820","created_at":"2026-07-05T06:38:57.734002+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PQZ2C6VXQMI","created_at":"2026-07-05T06:38:57.734002+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PQZ2C6VXQMIGOYL","created_at":"2026-07-05T06:38:57.734002+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PQZ2C6V","created_at":"2026-07-05T06:38:57.734002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05382","citing_title":"Synthetic Contrastive Reasoning for Multi-Table Q&A","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY","json":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY.json","graph_json":"https://pith.science/api/pith-number/5PQZ2C6VXQMIGOYLQLFSUPBZWY/graph.json","events_json":"https://pith.science/api/pith-number/5PQZ2C6VXQMIGOYLQLFSUPBZWY/events.json","paper":"https://pith.science/paper/5PQZ2C6V"},"agent_actions":{"view_html":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY","download_json":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY.json","view_paper":"https://pith.science/paper/5PQZ2C6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12820&json=true","fetch_graph":"https://pith.science/api/pith-number/5PQZ2C6VXQMIGOYLQLFSUPBZWY/graph.json","fetch_events":"https://pith.science/api/pith-number/5PQZ2C6VXQMIGOYLQLFSUPBZWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY/action/storage_attestation","attest_author":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY/action/author_attestation","sign_citation":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY/action/citation_signature","submit_replication":"https://pith.science/pith/5PQZ2C6VXQMIGOYLQLFSUPBZWY/action/replication_record"}},"created_at":"2026-07-05T06:38:57.734002+00:00","updated_at":"2026-07-05T06:38:57.734002+00:00"}