{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ID2LFJT44TUM4EQYWEIH3BRXQ","short_pith_number":"pith:7ID2LFJT","schema_version":"1.0","canonical_sha256":"fa07a59533e727467090c58883ec31bc3ce2efa263df83e71ed3499f39dd646e","source":{"kind":"arxiv","id":"2410.01943","version":1},"attestation_state":"computed","paper":{"title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Saberi, Fatma Ozcan, Gaurav Tarlok Kakkar, Hailong Li, Mohammadreza Pourreza, Ruoxi Sun, Sercan O. Arik, Shayan Talaei, Yeounoh Chung, Yu Gan","submitted_at":"2024-10-02T18:41:35Z","abstract_excerpt":"In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and selection. CHASE-SQL leverages LLMs' intrinsic knowledge to generate diverse and high-quality SQL candidates using different LLM generators with: (1) a divide-and-conquer method that decomposes complex queries into manageable sub-queries in a single LLM call; (2) chain-of-thought reasoning based on query execution plans, reflecting the steps a da"},"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":"2410.01943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T18:41:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"5f0da8f05e0adb329473b406845dabb2b14765daaaf929350fbfb6154fe92941","abstract_canon_sha256":"8969d7291491736d9301e9672c4f564e055ac4112141ffcca1d5dfc3ef115cd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:58.095253Z","signature_b64":"lgAp7L4zeo4dkyH7LoSj2jAN5gfoEtkzW+sptndp1rAh7jjnf/GJ+dA0bqYg5lAY+ZOZLDrswyVmlBXznitdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa07a59533e727467090c58883ec31bc3ce2efa263df83e71ed3499f39dd646e","last_reissued_at":"2026-07-05T09:14:58.094775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:58.094775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Saberi, Fatma Ozcan, Gaurav Tarlok Kakkar, Hailong Li, Mohammadreza Pourreza, Ruoxi Sun, Sercan O. Arik, Shayan Talaei, Yeounoh Chung, Yu Gan","submitted_at":"2024-10-02T18:41:35Z","abstract_excerpt":"In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and selection. CHASE-SQL leverages LLMs' intrinsic knowledge to generate diverse and high-quality SQL candidates using different LLM generators with: (1) a divide-and-conquer method that decomposes complex queries into manageable sub-queries in a single LLM call; (2) chain-of-thought reasoning based on query execution plans, reflecting the steps a da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01943","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/2410.01943/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":"2410.01943","created_at":"2026-07-05T09:14:58.094833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01943v1","created_at":"2026-07-05T09:14:58.094833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01943","created_at":"2026-07-05T09:14:58.094833+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ID2LFJT44TU","created_at":"2026-07-05T09:14:58.094833+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ID2LFJT44TUM4EQ","created_at":"2026-07-05T09:14:58.094833+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ID2LFJT","created_at":"2026-07-05T09:14:58.094833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05634","citing_title":"Bootstrapping Semantic Layer from Execution for Text-to-SQL","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28601","citing_title":"Database Context Compression for Text-to-SQL on Real-World Large Databases","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25838","citing_title":"Same Data, Different Schemas: Robustness of LLM-based Text-to-SQL","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21792","citing_title":"Residual Skill Optimization for Text-to-SQL Ensembles","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17680","citing_title":"When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19010","citing_title":"AgentNLQ: A General-Purpose Agent for Natural Language to SQL","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","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":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12319","citing_title":"Data-aware candidate selection in NL2SQL translation via small separating instances","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03465","citing_title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","ref_index":11,"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":23,"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":277,"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":292,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07041","citing_title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","ref_index":32,"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":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ","json":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ.json","graph_json":"https://pith.science/api/pith-number/7ID2LFJT44TUM4EQYWEIH3BRXQ/graph.json","events_json":"https://pith.science/api/pith-number/7ID2LFJT44TUM4EQYWEIH3BRXQ/events.json","paper":"https://pith.science/paper/7ID2LFJT"},"agent_actions":{"view_html":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ","download_json":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ.json","view_paper":"https://pith.science/paper/7ID2LFJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01943&json=true","fetch_graph":"https://pith.science/api/pith-number/7ID2LFJT44TUM4EQYWEIH3BRXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7ID2LFJT44TUM4EQYWEIH3BRXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ/action/storage_attestation","attest_author":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ/action/author_attestation","sign_citation":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ/action/citation_signature","submit_replication":"https://pith.science/pith/7ID2LFJT44TUM4EQYWEIH3BRXQ/action/replication_record"}},"created_at":"2026-07-05T09:14:58.094833+00:00","updated_at":"2026-07-05T09:14:58.094833+00:00"}