{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YA2JJ6UINONBTILIM2WCBDPFOT","short_pith_number":"pith:YA2JJ6UI","schema_version":"1.0","canonical_sha256":"c03494fa886b9a19a16866ac208de574fa7a1ac1c696d3e28b030eca98a5083a","source":{"kind":"arxiv","id":"2308.15363","version":4},"attestation_state":"computed","paper":{"title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Bolin Ding, Dawei Gao, Haibin Wang, Jingren Zhou, Xiuyu Sun, Yaliang Li, Yichen Qian","submitted_at":"2023-08-29T14:59:54Z","abstract_excerpt":"Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task. However, the absence of a systematical benchmark inhibits the development of designing effective, efficient and economic LLM-based Text-to-SQL solutions. To address this challenge, in this paper, we first conduct a systematical and extensive comparison over existing prompt engineering methods, including question representation, example selection and example organization, and with these experimental results, we elaborate their pros and cons. Based on these findings, we propose a new integrated solution, named DAIL"},"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":"2308.15363","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-08-29T14:59:54Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f4aac6c9048669f57888e4ab138d84e093337259834a9151d155c7af7f391c64","abstract_canon_sha256":"6fac0a6e7365220d8c8dccec2115595b70ae45f032111ea353946187adca5d40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:16.906866Z","signature_b64":"PSuv7PptnqcS/33BtJbhYnzhvwlzGc09aiDNwSAPTzrcMwOZMIi3G8VEK5W65RHMKNG+4pyVA8D8njAP4x1JDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c03494fa886b9a19a16866ac208de574fa7a1ac1c696d3e28b030eca98a5083a","last_reissued_at":"2026-07-05T07:14:16.906385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:16.906385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Bolin Ding, Dawei Gao, Haibin Wang, Jingren Zhou, Xiuyu Sun, Yaliang Li, Yichen Qian","submitted_at":"2023-08-29T14:59:54Z","abstract_excerpt":"Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task. However, the absence of a systematical benchmark inhibits the development of designing effective, efficient and economic LLM-based Text-to-SQL solutions. To address this challenge, in this paper, we first conduct a systematical and extensive comparison over existing prompt engineering methods, including question representation, example selection and example organization, and with these experimental results, we elaborate their pros and cons. Based on these findings, we propose a new integrated solution, named DAIL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15363","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/2308.15363/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":"2308.15363","created_at":"2026-07-05T07:14:16.906440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15363v4","created_at":"2026-07-05T07:14:16.906440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15363","created_at":"2026-07-05T07:14:16.906440+00:00"},{"alias_kind":"pith_short_12","alias_value":"YA2JJ6UINONB","created_at":"2026-07-05T07:14:16.906440+00:00"},{"alias_kind":"pith_short_16","alias_value":"YA2JJ6UINONBTILI","created_at":"2026-07-05T07:14:16.906440+00:00"},{"alias_kind":"pith_short_8","alias_value":"YA2JJ6UI","created_at":"2026-07-05T07:14:16.906440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12387","citing_title":"TAHOE: Text-to-SQL with Automated Hint Optimization from Experience","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11424","citing_title":"SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05679","citing_title":"Data Flow Control: Data Safety Policies for AI Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05906","citing_title":"ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04500","citing_title":"SANE Schema-aware Natural-language Evaluation of Biological Data","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03363","citing_title":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02109","citing_title":"BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":235,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28387","citing_title":"Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14174","citing_title":"Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21792","citing_title":"Residual Skill Optimization for Text-to-SQL Ensembles","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23978","citing_title":"LLM Agents Are the Antidote to Walled Gardens","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00303","citing_title":"Access Paths for Efficient Ordering with Large Language Models","ref_index":18,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01008","citing_title":"MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL","ref_index":8,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03057","citing_title":"Querying Structured Data Through Natural Language Using Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03465","citing_title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","ref_index":91,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":4,"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":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT","json":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT.json","graph_json":"https://pith.science/api/pith-number/YA2JJ6UINONBTILIM2WCBDPFOT/graph.json","events_json":"https://pith.science/api/pith-number/YA2JJ6UINONBTILIM2WCBDPFOT/events.json","paper":"https://pith.science/paper/YA2JJ6UI"},"agent_actions":{"view_html":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT","download_json":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT.json","view_paper":"https://pith.science/paper/YA2JJ6UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15363&json=true","fetch_graph":"https://pith.science/api/pith-number/YA2JJ6UINONBTILIM2WCBDPFOT/graph.json","fetch_events":"https://pith.science/api/pith-number/YA2JJ6UINONBTILIM2WCBDPFOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT/action/storage_attestation","attest_author":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT/action/author_attestation","sign_citation":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT/action/citation_signature","submit_replication":"https://pith.science/pith/YA2JJ6UINONBTILIM2WCBDPFOT/action/replication_record"}},"created_at":"2026-07-05T07:14:16.906440+00:00","updated_at":"2026-07-05T07:14:16.906440+00:00"}