{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SMWCGYZLKXNYGWNEFE4VC7W6FO","short_pith_number":"pith:SMWCGYZL","schema_version":"1.0","canonical_sha256":"932c23632b55db8359a42939517ede2b8f6852b954bfbf318faf3175fdb96347","source":{"kind":"arxiv","id":"2204.00498","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dzmitry Bahdanau, Nitarshan Rajkumar, Raymond Li","submitted_at":"2022-03-15T17:23:53Z","abstract_excerpt":"We perform an empirical evaluation of Text-to-SQL capabilities of the Codex language model. We find that, without any finetuning, Codex is a strong baseline on the Spider benchmark; we also analyze the failure modes of Codex in this setting. Furthermore, we demonstrate on the GeoQuery and Scholar benchmarks that a small number of in-domain examples provided in the prompt enables Codex to perform better than state-of-the-art models finetuned on such few-shot examples."},"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":"2204.00498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T17:23:53Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"f96f9b072148e95e711a7ff584be9ed7acd6da62392ccdc8ea9ab80c1f290cd4","abstract_canon_sha256":"d579cf5090181b659068b55c2f5cec28908478c247509e05c0c304bb876bb499"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:48.000592Z","signature_b64":"a5PIm6wLz3PhWktwBaZxP5UVM6uHx/P9Y5kSuPorl3MDG/8e0KtQKrjIRBCwwcNv1SiTMjxHSRt4M4we7xKoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"932c23632b55db8359a42939517ede2b8f6852b954bfbf318faf3175fdb96347","last_reissued_at":"2026-07-05T04:10:48.000193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:48.000193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dzmitry Bahdanau, Nitarshan Rajkumar, Raymond Li","submitted_at":"2022-03-15T17:23:53Z","abstract_excerpt":"We perform an empirical evaluation of Text-to-SQL capabilities of the Codex language model. We find that, without any finetuning, Codex is a strong baseline on the Spider benchmark; we also analyze the failure modes of Codex in this setting. Furthermore, we demonstrate on the GeoQuery and Scholar benchmarks that a small number of in-domain examples provided in the prompt enables Codex to perform better than state-of-the-art models finetuned on such few-shot examples."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00498","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/2204.00498/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":"2204.00498","created_at":"2026-07-05T04:10:48.000257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00498v1","created_at":"2026-07-05T04:10:48.000257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00498","created_at":"2026-07-05T04:10:48.000257+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMWCGYZLKXNY","created_at":"2026-07-05T04:10:48.000257+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMWCGYZLKXNYGWNE","created_at":"2026-07-05T04:10:48.000257+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMWCGYZL","created_at":"2026-07-05T04:10:48.000257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17680","citing_title":"When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18766","citing_title":"Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2304.05128","citing_title":"Teaching Large Language Models to Self-Debug","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10973","citing_title":"CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":239,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07041","citing_title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06736","citing_title":"SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO","json":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO.json","graph_json":"https://pith.science/api/pith-number/SMWCGYZLKXNYGWNEFE4VC7W6FO/graph.json","events_json":"https://pith.science/api/pith-number/SMWCGYZLKXNYGWNEFE4VC7W6FO/events.json","paper":"https://pith.science/paper/SMWCGYZL"},"agent_actions":{"view_html":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO","download_json":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO.json","view_paper":"https://pith.science/paper/SMWCGYZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00498&json=true","fetch_graph":"https://pith.science/api/pith-number/SMWCGYZLKXNYGWNEFE4VC7W6FO/graph.json","fetch_events":"https://pith.science/api/pith-number/SMWCGYZLKXNYGWNEFE4VC7W6FO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO/action/storage_attestation","attest_author":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO/action/author_attestation","sign_citation":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO/action/citation_signature","submit_replication":"https://pith.science/pith/SMWCGYZLKXNYGWNEFE4VC7W6FO/action/replication_record"}},"created_at":"2026-07-05T04:10:48.000257+00:00","updated_at":"2026-07-05T04:10:48.000257+00:00"}