{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NH5TL3435S3SJTKPBD2IEJK7HS","short_pith_number":"pith:NH5TL343","schema_version":"1.0","canonical_sha256":"69fb35ef9becb724cd4f08f482255f3c8bbe4c8640e21b0c5b36456f1f5e3a0a","source":{"kind":"arxiv","id":"2205.12682","version":1},"attestation_state":"computed","paper":{"title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dongmei Zhang, Fan Zhou, Haoyu Dong, Mengkang Hu, Shi Han, Zhoujun Cheng","submitted_at":"2022-05-25T11:44:11Z","abstract_excerpt":"Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks. However, auto-regressive PLMs are challenged by recent emerging numerical reasoning datasets, such as TAT-QA, due to the error-prone implicit calculation. In this paper, we present TaCube, to pre-compute aggregation/arithmetic results for the table in advance, so that they are handy and readily available for PLMs to answer numerical reasoning questions. TaCube sys"},"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":"2205.12682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-05-25T11:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"9e01f2518a43835a2d6632ca336208d8fd5b8f00573d403d56d0333d5ca25e63","abstract_canon_sha256":"5d30125c60d179daf45312de9f3f501bdded26e33d110500934b160eaaa8b546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:28.743444Z","signature_b64":"UWOmmjMBS1i/bH9t9GDm5lOUMU29uEVqem4b94mC28ToTYL9LTU+vve+X41KC0FxxZpKw/0yHDzio5paQks5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69fb35ef9becb724cd4f08f482255f3c8bbe4c8640e21b0c5b36456f1f5e3a0a","last_reissued_at":"2026-07-05T04:26:28.742964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:28.742964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dongmei Zhang, Fan Zhou, Haoyu Dong, Mengkang Hu, Shi Han, Zhoujun Cheng","submitted_at":"2022-05-25T11:44:11Z","abstract_excerpt":"Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks. However, auto-regressive PLMs are challenged by recent emerging numerical reasoning datasets, such as TAT-QA, due to the error-prone implicit calculation. In this paper, we present TaCube, to pre-compute aggregation/arithmetic results for the table in advance, so that they are handy and readily available for PLMs to answer numerical reasoning questions. TaCube sys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12682","kind":"arxiv","version":1},"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/2205.12682/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":"2205.12682","created_at":"2026-07-05T04:26:28.743017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12682v1","created_at":"2026-07-05T04:26:28.743017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12682","created_at":"2026-07-05T04:26:28.743017+00:00"},{"alias_kind":"pith_short_12","alias_value":"NH5TL3435S3S","created_at":"2026-07-05T04:26:28.743017+00:00"},{"alias_kind":"pith_short_16","alias_value":"NH5TL3435S3SJTKP","created_at":"2026-07-05T04:26:28.743017+00:00"},{"alias_kind":"pith_short_8","alias_value":"NH5TL343","created_at":"2026-07-05T04:26:28.743017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12981","citing_title":"MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS","json":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS.json","graph_json":"https://pith.science/api/pith-number/NH5TL3435S3SJTKPBD2IEJK7HS/graph.json","events_json":"https://pith.science/api/pith-number/NH5TL3435S3SJTKPBD2IEJK7HS/events.json","paper":"https://pith.science/paper/NH5TL343"},"agent_actions":{"view_html":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS","download_json":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS.json","view_paper":"https://pith.science/paper/NH5TL343","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12682&json=true","fetch_graph":"https://pith.science/api/pith-number/NH5TL3435S3SJTKPBD2IEJK7HS/graph.json","fetch_events":"https://pith.science/api/pith-number/NH5TL3435S3SJTKPBD2IEJK7HS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS/action/storage_attestation","attest_author":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS/action/author_attestation","sign_citation":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS/action/citation_signature","submit_replication":"https://pith.science/pith/NH5TL3435S3SJTKPBD2IEJK7HS/action/replication_record"}},"created_at":"2026-07-05T04:26:28.743017+00:00","updated_at":"2026-07-05T04:26:28.743017+00:00"}