{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7RUC6QUKNKQ2PLEMMWMZFCXBOM","short_pith_number":"pith:7RUC6QUK","schema_version":"1.0","canonical_sha256":"fc682f428a6aa1a7ac8c6599928ae1730befaf5379eb89d105994c1a07eb5151","source":{"kind":"arxiv","id":"2509.09234","version":1},"attestation_state":"computed","paper":{"title":"Agentic LLMs for Question Answering over Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohit Gupta, Rahul Bouri, Rishit Tyagi","submitted_at":"2025-09-11T08:12:38Z","abstract_excerpt":"Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query gene"},"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":"2509.09234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T08:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"ba325bc90de9a3416147c38c764be8f3d8919637b53d3869bf17aee62550720c","abstract_canon_sha256":"611fe28abf03d761c4578afc080105b5d7916bfcb7123d853c17c16f798d0105"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:32.039199Z","signature_b64":"EusAzd2bk8xa1ZCzmMVBR6Wp5wuZ4cXxakKojjA6OthHan2PsnmSRVva9SixrPePwQS/KNcgK/Fbr/IqMNPyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc682f428a6aa1a7ac8c6599928ae1730befaf5379eb89d105994c1a07eb5151","last_reissued_at":"2026-07-05T12:09:32.038770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:32.038770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agentic LLMs for Question Answering over Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohit Gupta, Rahul Bouri, Rishit Tyagi","submitted_at":"2025-09-11T08:12:38Z","abstract_excerpt":"Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09234","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/2509.09234/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":"2509.09234","created_at":"2026-07-05T12:09:32.038833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09234v1","created_at":"2026-07-05T12:09:32.038833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09234","created_at":"2026-07-05T12:09:32.038833+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RUC6QUKNKQ2","created_at":"2026-07-05T12:09:32.038833+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RUC6QUKNKQ2PLEM","created_at":"2026-07-05T12:09:32.038833+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RUC6QUK","created_at":"2026-07-05T12:09:32.038833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM","json":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM.json","graph_json":"https://pith.science/api/pith-number/7RUC6QUKNKQ2PLEMMWMZFCXBOM/graph.json","events_json":"https://pith.science/api/pith-number/7RUC6QUKNKQ2PLEMMWMZFCXBOM/events.json","paper":"https://pith.science/paper/7RUC6QUK"},"agent_actions":{"view_html":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM","download_json":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM.json","view_paper":"https://pith.science/paper/7RUC6QUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09234&json=true","fetch_graph":"https://pith.science/api/pith-number/7RUC6QUKNKQ2PLEMMWMZFCXBOM/graph.json","fetch_events":"https://pith.science/api/pith-number/7RUC6QUKNKQ2PLEMMWMZFCXBOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM/action/storage_attestation","attest_author":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM/action/author_attestation","sign_citation":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM/action/citation_signature","submit_replication":"https://pith.science/pith/7RUC6QUKNKQ2PLEMMWMZFCXBOM/action/replication_record"}},"created_at":"2026-07-05T12:09:32.038833+00:00","updated_at":"2026-07-05T12:09:32.038833+00:00"}