{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IK3S44IRBRHEULSBGLECITRORO","short_pith_number":"pith:IK3S44IR","schema_version":"1.0","canonical_sha256":"42b72e71110c4e4a2e4132c8244e2e8b81a6db76bba91cb7243dd6448ce8ad4b","source":{"kind":"arxiv","id":"2405.07467","version":1},"attestation_state":"computed","paper":{"title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Choongwon Park, Dongjun Lee, Heesoo Park, Jaehyuk Kim","submitted_at":"2024-05-13T04:59:32Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of human experts on benchmarks that include complex schemas and queries, such as BIRD. This study considers the sensitivity of LLMs to the prompts and introduces a novel approach that leverages multiple prompts to explore a broader search space for possible answers and effectively aggregate them. Specifically, we robustly refine the database schema thr"},"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":"2405.07467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T04:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"5f1e0ac21207142ea3c38c7c5bd1aaf9c968efaaf1c32f1a9def6595e32737f8","abstract_canon_sha256":"1172abfe4f2aa4c8cae6543c4f490502682c4c01bffd4b4bbfd9dffdcb2a0165"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:22.906932Z","signature_b64":"czywIZ0Tnzaqvptqpnzx/dGIVBl1OWq2s5Hy0XVfBYXwiBbC9XCQ1l0t1l6drX0+Gt1LW2g1hrQZAeuCFQLkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42b72e71110c4e4a2e4132c8244e2e8b81a6db76bba91cb7243dd6448ce8ad4b","last_reissued_at":"2026-07-05T08:18:22.906525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:22.906525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Choongwon Park, Dongjun Lee, Heesoo Park, Jaehyuk Kim","submitted_at":"2024-05-13T04:59:32Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of human experts on benchmarks that include complex schemas and queries, such as BIRD. This study considers the sensitivity of LLMs to the prompts and introduces a novel approach that leverages multiple prompts to explore a broader search space for possible answers and effectively aggregate them. Specifically, we robustly refine the database schema thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07467","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/2405.07467/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":"2405.07467","created_at":"2026-07-05T08:18:22.906582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07467v1","created_at":"2026-07-05T08:18:22.906582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07467","created_at":"2026-07-05T08:18:22.906582+00:00"},{"alias_kind":"pith_short_12","alias_value":"IK3S44IRBRHE","created_at":"2026-07-05T08:18:22.906582+00:00"},{"alias_kind":"pith_short_16","alias_value":"IK3S44IRBRHEULSB","created_at":"2026-07-05T08:18:22.906582+00:00"},{"alias_kind":"pith_short_8","alias_value":"IK3S44IR","created_at":"2026-07-05T08:18:22.906582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26613","citing_title":"EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28028","citing_title":"Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO","json":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO.json","graph_json":"https://pith.science/api/pith-number/IK3S44IRBRHEULSBGLECITRORO/graph.json","events_json":"https://pith.science/api/pith-number/IK3S44IRBRHEULSBGLECITRORO/events.json","paper":"https://pith.science/paper/IK3S44IR"},"agent_actions":{"view_html":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO","download_json":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO.json","view_paper":"https://pith.science/paper/IK3S44IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07467&json=true","fetch_graph":"https://pith.science/api/pith-number/IK3S44IRBRHEULSBGLECITRORO/graph.json","fetch_events":"https://pith.science/api/pith-number/IK3S44IRBRHEULSBGLECITRORO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO/action/storage_attestation","attest_author":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO/action/author_attestation","sign_citation":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO/action/citation_signature","submit_replication":"https://pith.science/pith/IK3S44IRBRHEULSBGLECITRORO/action/replication_record"}},"created_at":"2026-07-05T08:18:22.906582+00:00","updated_at":"2026-07-05T08:18:22.906582+00:00"}