{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HRE3BHO6ZCMHXZ5GLQ64MAJEYV","short_pith_number":"pith:HRE3BHO6","schema_version":"1.0","canonical_sha256":"3c49b09ddec8987be7a65c3dc60124c57d5915feae0e0a4c6435b987a87be760","source":{"kind":"arxiv","id":"2406.10593","version":2},"attestation_state":"computed","paper":{"title":"QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.AI","authors_text":"Bingxuan Wang, Chuanyi Liu, Haining Yu, Tiancheng Zhao, Xiang Li, Xiangzhan Yu, Yinggang Sun, Ziming Guo","submitted_at":"2024-06-15T10:54:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions. It is desired to enhance LLMs to handle multiple types of questions in multi-turn Text-to-SQL tasks. To address this, we propose a novel data augmentation method, called QDA-SQL, which generates multiple types of multi-turn Q\\&A pairs using LLMs. In QDA-SQL, we introduce a method incorporating validation and correction mechanisms to handle comple"},"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":"2406.10593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-15T10:54:54Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"beb659933fe7dbde827fe1fc8df183f193a4be73147352f5f9b5088ff7062004","abstract_canon_sha256":"2aaa51f499b8c7a6a4360a42ef811bdd44110cde686077b9aa77b133dc0078cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:33.482730Z","signature_b64":"ciY1T/ojbBivFPVFJU56u6Bjg3iY95QzwwgAeeLi/Vm994hhABFebJci5wdTDQm0x8XXLFV35xN2xaYTaeDjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c49b09ddec8987be7a65c3dc60124c57d5915feae0e0a4c6435b987a87be760","last_reissued_at":"2026-07-05T09:33:33.482249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:33.482249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.AI","authors_text":"Bingxuan Wang, Chuanyi Liu, Haining Yu, Tiancheng Zhao, Xiang Li, Xiangzhan Yu, Yinggang Sun, Ziming Guo","submitted_at":"2024-06-15T10:54:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions. It is desired to enhance LLMs to handle multiple types of questions in multi-turn Text-to-SQL tasks. To address this, we propose a novel data augmentation method, called QDA-SQL, which generates multiple types of multi-turn Q\\&A pairs using LLMs. In QDA-SQL, we introduce a method incorporating validation and correction mechanisms to handle comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10593","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/2406.10593/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":"2406.10593","created_at":"2026-07-05T09:33:33.482304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10593v2","created_at":"2026-07-05T09:33:33.482304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10593","created_at":"2026-07-05T09:33:33.482304+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRE3BHO6ZCMH","created_at":"2026-07-05T09:33:33.482304+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRE3BHO6ZCMHXZ5G","created_at":"2026-07-05T09:33:33.482304+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRE3BHO6","created_at":"2026-07-05T09:33:33.482304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23838","citing_title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","ref_index":112,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV","json":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV.json","graph_json":"https://pith.science/api/pith-number/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/graph.json","events_json":"https://pith.science/api/pith-number/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/events.json","paper":"https://pith.science/paper/HRE3BHO6"},"agent_actions":{"view_html":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV","download_json":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV.json","view_paper":"https://pith.science/paper/HRE3BHO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10593&json=true","fetch_graph":"https://pith.science/api/pith-number/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/graph.json","fetch_events":"https://pith.science/api/pith-number/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/action/storage_attestation","attest_author":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/action/author_attestation","sign_citation":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/action/citation_signature","submit_replication":"https://pith.science/pith/HRE3BHO6ZCMHXZ5GLQ64MAJEYV/action/replication_record"}},"created_at":"2026-07-05T09:33:33.482304+00:00","updated_at":"2026-07-05T09:33:33.482304+00:00"}