{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TFRBB32R5MT7EILPN2KF26LPE","short_pith_number":"pith:3TFRBB32","schema_version":"1.0","canonical_sha256":"dccb10877a8f593f910b7b74a2ebcb79278118d91f4ab464ef862fde2ce85286","source":{"kind":"arxiv","id":"2410.12846","version":4},"attestation_state":"computed","paper":{"title":"Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianzhong Qi, Junhao Gan, Yuxiang Wang","submitted_at":"2024-10-10T05:34:00Z","abstract_excerpt":"Question answering on free-form tables (a.k.a. TableQA) is a challenging task because of the flexible structure and complex schema of tables. Recent studies use Large Language Models (LLMs) for this task, exploiting their capability in understanding the questions and tabular data, which are typically given in natural language and contain many textual fields, respectively. While this approach has shown promising results, it overlooks the challenges brought by numerical values which are common in tabular data, and LLMs are known to struggle with such values. We aim to address this issue, and we "},"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":"2410.12846","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T05:34:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d37cacc4b3df577500b0608cb87cfb2651884cafb4c7c61596286d54d9f85219","abstract_canon_sha256":"d21be34466d35389d8875b355731dd9e5f433d534d89fa37ba8c9013b670c0d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:37.108487Z","signature_b64":"2xvLonlWaODypjjZZ6UfP9q8l6sj2ZOGnOiUKrEHqZKvlmGl2CvhN5l/OEKnIwX2QBVKpfx8snDFt0COMhtfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dccb10877a8f593f910b7b74a2ebcb79278118d91f4ab464ef862fde2ce85286","last_reissued_at":"2026-07-05T11:21:37.107906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:37.107906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianzhong Qi, Junhao Gan, Yuxiang Wang","submitted_at":"2024-10-10T05:34:00Z","abstract_excerpt":"Question answering on free-form tables (a.k.a. TableQA) is a challenging task because of the flexible structure and complex schema of tables. Recent studies use Large Language Models (LLMs) for this task, exploiting their capability in understanding the questions and tabular data, which are typically given in natural language and contain many textual fields, respectively. While this approach has shown promising results, it overlooks the challenges brought by numerical values which are common in tabular data, and LLMs are known to struggle with such values. We aim to address this issue, and we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12846","kind":"arxiv","version":4},"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/2410.12846/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":"2410.12846","created_at":"2026-07-05T11:21:37.107979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12846v4","created_at":"2026-07-05T11:21:37.107979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12846","created_at":"2026-07-05T11:21:37.107979+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TFRBB32R5MT","created_at":"2026-07-05T11:21:37.107979+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TFRBB32R5MT7EIL","created_at":"2026-07-05T11:21:37.107979+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TFRBB32","created_at":"2026-07-05T11:21:37.107979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22264","citing_title":"MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Steps","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE","json":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE.json","graph_json":"https://pith.science/api/pith-number/3TFRBB32R5MT7EILPN2KF26LPE/graph.json","events_json":"https://pith.science/api/pith-number/3TFRBB32R5MT7EILPN2KF26LPE/events.json","paper":"https://pith.science/paper/3TFRBB32"},"agent_actions":{"view_html":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE","download_json":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE.json","view_paper":"https://pith.science/paper/3TFRBB32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12846&json=true","fetch_graph":"https://pith.science/api/pith-number/3TFRBB32R5MT7EILPN2KF26LPE/graph.json","fetch_events":"https://pith.science/api/pith-number/3TFRBB32R5MT7EILPN2KF26LPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE/action/storage_attestation","attest_author":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE/action/author_attestation","sign_citation":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE/action/citation_signature","submit_replication":"https://pith.science/pith/3TFRBB32R5MT7EILPN2KF26LPE/action/replication_record"}},"created_at":"2026-07-05T11:21:37.107979+00:00","updated_at":"2026-07-05T11:21:37.107979+00:00"}