{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DIDKR6B53DGQADV2433VDSDLZL","short_pith_number":"pith:DIDKR6B5","schema_version":"1.0","canonical_sha256":"1a06a8f83dd8cd000ebae6f751c86bcae2f504643be3460d5aebaffc86c6c09b","source":{"kind":"arxiv","id":"2304.11015","version":3},"attestation_state":"computed","paper":{"title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.HC"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Mohammadreza Pourreza","submitted_at":"2023-04-21T15:02:18Z","abstract_excerpt":"There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with 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":"2304.11015","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-21T15:02:18Z","cross_cats_sorted":["cs.AI","cs.DB","cs.HC"],"title_canon_sha256":"e9e7119b495e1eadeffa2f3368febb6a2399734385baf4667a96bbee3dc84e69","abstract_canon_sha256":"5447d1389882caca003ab473da568c905adb829a3421fbdd12f7511d53a200bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:28.226862Z","signature_b64":"bfYw1FuL7iHQq1+hONyy3+j4UHLdFyB8SFz556pMVyY6tXPnwpgzagx0aqvFu1SRgZXp+KR97fDvQ3fJTmZECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a06a8f83dd8cd000ebae6f751c86bcae2f504643be3460d5aebaffc86c6c09b","last_reissued_at":"2026-07-05T07:08:28.226426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:28.226426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.HC"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Mohammadreza Pourreza","submitted_at":"2023-04-21T15:02:18Z","abstract_excerpt":"There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11015","kind":"arxiv","version":3},"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/2304.11015/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":"2304.11015","created_at":"2026-07-05T07:08:28.226482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11015v3","created_at":"2026-07-05T07:08:28.226482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11015","created_at":"2026-07-05T07:08:28.226482+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIDKR6B53DGQ","created_at":"2026-07-05T07:08:28.226482+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIDKR6B53DGQADV2","created_at":"2026-07-05T07:08:28.226482+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIDKR6B5","created_at":"2026-07-05T07:08:28.226482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01992","citing_title":"Traceable Fault Diagnosis for Battery Energy Storage Systems via Retrieval-Augmented Multi-Agent O&M Assistant","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04500","citing_title":"SANE Schema-aware Natural-language Evaluation of Biological Data","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00828","citing_title":"Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02109","citing_title":"BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28387","citing_title":"Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26394","citing_title":"Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22843","citing_title":"Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model","ref_index":5,"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":24,"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":8,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03714","citing_title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02815","citing_title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL","json":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL.json","graph_json":"https://pith.science/api/pith-number/DIDKR6B53DGQADV2433VDSDLZL/graph.json","events_json":"https://pith.science/api/pith-number/DIDKR6B53DGQADV2433VDSDLZL/events.json","paper":"https://pith.science/paper/DIDKR6B5"},"agent_actions":{"view_html":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL","download_json":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL.json","view_paper":"https://pith.science/paper/DIDKR6B5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11015&json=true","fetch_graph":"https://pith.science/api/pith-number/DIDKR6B53DGQADV2433VDSDLZL/graph.json","fetch_events":"https://pith.science/api/pith-number/DIDKR6B53DGQADV2433VDSDLZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL/action/storage_attestation","attest_author":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL/action/author_attestation","sign_citation":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL/action/citation_signature","submit_replication":"https://pith.science/pith/DIDKR6B53DGQADV2433VDSDLZL/action/replication_record"}},"created_at":"2026-07-05T07:08:28.226482+00:00","updated_at":"2026-07-05T07:08:28.226482+00:00"}