{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WW6XXKX6OYBDEIDEUL5I26ZNWG","short_pith_number":"pith:WW6XXKX6","schema_version":"1.0","canonical_sha256":"b5bd7baafe7602322064a2fa8d7b2db1b772ee5e2590c0ad258acdb1573fd683","source":{"kind":"arxiv","id":"2403.09732","version":4},"attestation_state":"computed","paper":{"title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Zhang, Guoqing Du, Hangyu Mao, Jingjing Zhao, Rui Zhao, Sun Yang, Xiang Wang, Xiaoru Hu, Yuxiao Ye, Zhishuai Li, Ziyue Li","submitted_at":"2024-03-13T02:32:41Z","abstract_excerpt":"Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM) on in-context learning, achieving significant results. Nevertheless, they face challenges when dealing with verbose database information and complex user intentions. This paper presents a two-stage framework to enhance the performance of current LLM-based natural language to SQL systems. We first introduce a novel prompt representation, called reference-enhanced representation, which includes schema information and randomly sampled cell values from tables to instruct LLMs in generating SQL queri"},"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":"2403.09732","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T02:32:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"676369cf4581073ec3835218b8d12f95bb11c03e601562f2e7379ff86067d23e","abstract_canon_sha256":"19e37111c56a220f8358c941c148ae461a531dccdda0cca23eb130cee648f9e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:21.747943Z","signature_b64":"nXntxEkuwmQImWG1Kf+tlNhFu/e00QVk8Gp5UgAgJMhg2/95+Q7bXyR7WrPsyyQUFi3H68zSgl1FnVBorgsRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5bd7baafe7602322064a2fa8d7b2db1b772ee5e2590c0ad258acdb1573fd683","last_reissued_at":"2026-07-05T08:26:21.747475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:21.747475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Zhang, Guoqing Du, Hangyu Mao, Jingjing Zhao, Rui Zhao, Sun Yang, Xiang Wang, Xiaoru Hu, Yuxiao Ye, Zhishuai Li, Ziyue Li","submitted_at":"2024-03-13T02:32:41Z","abstract_excerpt":"Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM) on in-context learning, achieving significant results. Nevertheless, they face challenges when dealing with verbose database information and complex user intentions. This paper presents a two-stage framework to enhance the performance of current LLM-based natural language to SQL systems. We first introduce a novel prompt representation, called reference-enhanced representation, which includes schema information and randomly sampled cell values from tables to instruct LLMs in generating SQL queri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09732","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/2403.09732/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":"2403.09732","created_at":"2026-07-05T08:26:21.747529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09732v4","created_at":"2026-07-05T08:26:21.747529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09732","created_at":"2026-07-05T08:26:21.747529+00:00"},{"alias_kind":"pith_short_12","alias_value":"WW6XXKX6OYBD","created_at":"2026-07-05T08:26:21.747529+00:00"},{"alias_kind":"pith_short_16","alias_value":"WW6XXKX6OYBDEIDE","created_at":"2026-07-05T08:26:21.747529+00:00"},{"alias_kind":"pith_short_8","alias_value":"WW6XXKX6","created_at":"2026-07-05T08:26:21.747529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28601","citing_title":"Database Context Compression for Text-to-SQL on Real-World Large Databases","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23693","citing_title":"EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2601.17942","citing_title":"LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting","ref_index":10,"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":115,"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":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG","json":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG.json","graph_json":"https://pith.science/api/pith-number/WW6XXKX6OYBDEIDEUL5I26ZNWG/graph.json","events_json":"https://pith.science/api/pith-number/WW6XXKX6OYBDEIDEUL5I26ZNWG/events.json","paper":"https://pith.science/paper/WW6XXKX6"},"agent_actions":{"view_html":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG","download_json":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG.json","view_paper":"https://pith.science/paper/WW6XXKX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09732&json=true","fetch_graph":"https://pith.science/api/pith-number/WW6XXKX6OYBDEIDEUL5I26ZNWG/graph.json","fetch_events":"https://pith.science/api/pith-number/WW6XXKX6OYBDEIDEUL5I26ZNWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG/action/storage_attestation","attest_author":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG/action/author_attestation","sign_citation":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG/action/citation_signature","submit_replication":"https://pith.science/pith/WW6XXKX6OYBDEIDEUL5I26ZNWG/action/replication_record"}},"created_at":"2026-07-05T08:26:21.747529+00:00","updated_at":"2026-07-05T08:26:21.747529+00:00"}