{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEV2MNWGJUV5YSKCSGUIXQG5XB","short_pith_number":"pith:EEV2MNWG","schema_version":"1.0","canonical_sha256":"212ba636c64d2bdc494291a88bc0ddb870e7bbc9fb2c959db4d6707ec0527b44","source":{"kind":"arxiv","id":"2406.17961","version":2},"attestation_state":"computed","paper":{"title":"NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Md Mahadi Hasan Nahid","submitted_at":"2024-06-25T22:40:03Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. However, their performance in tasks involving tabular data, especially those requiring symbolic reasoning, faces challenges due to the structural variance and inconsistency in table cell values often found in web tables. In this paper, we introduce NormTab, a novel framework aimed at enhancing the symbolic reasoning performance of LLMs by normalizing web tables. We study table normalization as a stand-alone, one-time preprocessing step using LLMs to support symbo"},"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":"2406.17961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T22:40:03Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"title_canon_sha256":"26ed31bbf6676092ff9c681f95071cba2980e2d172816fa45dcfbb454c8b7113","abstract_canon_sha256":"adc9be1371b3ef2077002e72fc58e85ead44109d7ae8e92f4f782d02ecceaba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:36.533020Z","signature_b64":"w7DM9/7U9xII0uftxatrDVRKev85GzXgE6zG4aBt1Jwr89PU+bSPo2WSzivyi5Q+QZpuUU4VSaMCpNicOXYZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"212ba636c64d2bdc494291a88bc0ddb870e7bbc9fb2c959db4d6707ec0527b44","last_reissued_at":"2026-07-05T10:43:36.529340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:36.529340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Md Mahadi Hasan Nahid","submitted_at":"2024-06-25T22:40:03Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. However, their performance in tasks involving tabular data, especially those requiring symbolic reasoning, faces challenges due to the structural variance and inconsistency in table cell values often found in web tables. In this paper, we introduce NormTab, a novel framework aimed at enhancing the symbolic reasoning performance of LLMs by normalizing web tables. We study table normalization as a stand-alone, one-time preprocessing step using LLMs to support symbo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17961","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/2406.17961/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":"2406.17961","created_at":"2026-07-05T10:43:36.530965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17961v2","created_at":"2026-07-05T10:43:36.530965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17961","created_at":"2026-07-05T10:43:36.530965+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEV2MNWGJUV5","created_at":"2026-07-05T10:43:36.530965+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEV2MNWGJUV5YSKC","created_at":"2026-07-05T10:43:36.530965+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEV2MNWG","created_at":"2026-07-05T10:43:36.530965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17110","citing_title":"TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB","json":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB.json","graph_json":"https://pith.science/api/pith-number/EEV2MNWGJUV5YSKCSGUIXQG5XB/graph.json","events_json":"https://pith.science/api/pith-number/EEV2MNWGJUV5YSKCSGUIXQG5XB/events.json","paper":"https://pith.science/paper/EEV2MNWG"},"agent_actions":{"view_html":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB","download_json":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB.json","view_paper":"https://pith.science/paper/EEV2MNWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17961&json=true","fetch_graph":"https://pith.science/api/pith-number/EEV2MNWGJUV5YSKCSGUIXQG5XB/graph.json","fetch_events":"https://pith.science/api/pith-number/EEV2MNWGJUV5YSKCSGUIXQG5XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB/action/storage_attestation","attest_author":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB/action/author_attestation","sign_citation":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB/action/citation_signature","submit_replication":"https://pith.science/pith/EEV2MNWGJUV5YSKCSGUIXQG5XB/action/replication_record"}},"created_at":"2026-07-05T10:43:36.530965+00:00","updated_at":"2026-07-05T10:43:36.530965+00:00"}