{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7PWO22UI74GVXIHXNKBSNOPD6C","short_pith_number":"pith:7PWO22UI","schema_version":"1.0","canonical_sha256":"fbeced6a88ff0d5ba0f76a8326b9e3f0b96b39528c853833fa074bcaa0a6b323","source":{"kind":"arxiv","id":"2405.16755","version":3},"attestation_state":"computed","paper":{"title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Saberi, Azalia Mirhoseini, Mohammadreza Pourreza, Shayan Talaei, Yu-Chen Chang","submitted_at":"2024-05-27T01:54:16Z","abstract_excerpt":"Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. Effective text-to-SQL synthesis can become very challenging due to (i) the extensive size of database catalogs (descriptions of tables and their columns) and database values, (ii) reasoning over large database schemas, (iii) ensuring the functional validity of the generated queries, and (iv) navigating the ambiguities of natural language questions. We introduce CHESS, a Large Language Model (LLM) based multi-agent framework for efficient and scalable SQL synthesis, comprising fou"},"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":"2405.16755","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T01:54:16Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"51bde4a65358a2c3c620aa9b06c802754c8c9029d43dd4b849f433cec8a428f3","abstract_canon_sha256":"f98c47fbb8e435cecbed6972cbe9a4eba63c05b78d5812be6c38225e32136904"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T11:18:05.505634Z","signature_b64":"+wNwtIh9Zl6XrLwPnKFjNHZLDpA+12dUVkLPTNRKOX4cdp2NdDZaWDRvHu2V+NfbHbjkV+lIgRjShvXsOjoVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbeced6a88ff0d5ba0f76a8326b9e3f0b96b39528c853833fa074bcaa0a6b323","last_reissued_at":"2026-05-19T11:18:05.503924Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T11:18:05.503924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Saberi, Azalia Mirhoseini, Mohammadreza Pourreza, Shayan Talaei, Yu-Chen Chang","submitted_at":"2024-05-27T01:54:16Z","abstract_excerpt":"Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. Effective text-to-SQL synthesis can become very challenging due to (i) the extensive size of database catalogs (descriptions of tables and their columns) and database values, (ii) reasoning over large database schemas, (iii) ensuring the functional validity of the generated queries, and (iv) navigating the ambiguities of natural language questions. We introduce CHESS, a Large Language Model (LLM) based multi-agent framework for efficient and scalable SQL synthesis, comprising fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16755","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/2405.16755/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":"2405.16755","created_at":"2026-05-19T11:18:05.504001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16755v3","created_at":"2026-05-19T11:18:05.504001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16755","created_at":"2026-05-19T11:18:05.504001+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PWO22UI74GV","created_at":"2026-05-19T11:18:05.504001+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PWO22UI74GVXIHX","created_at":"2026-05-19T11:18:05.504001+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PWO22UI","created_at":"2026-05-19T11:18:05.504001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2510.17586","citing_title":"DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2511.01008","citing_title":"MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2603.04334","citing_title":"SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13045","citing_title":"Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12319","citing_title":"Data-aware candidate selection in NL2SQL translation via small separating instances","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03465","citing_title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05260","citing_title":"SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems via Model Context Protocol","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21414","citing_title":"SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16493","citing_title":"NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09470","citing_title":"Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07041","citing_title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02815","citing_title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C","json":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C.json","graph_json":"https://pith.science/api/pith-number/7PWO22UI74GVXIHXNKBSNOPD6C/graph.json","events_json":"https://pith.science/api/pith-number/7PWO22UI74GVXIHXNKBSNOPD6C/events.json","paper":"https://pith.science/paper/7PWO22UI"},"agent_actions":{"view_html":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C","download_json":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C.json","view_paper":"https://pith.science/paper/7PWO22UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16755&json=true","fetch_graph":"https://pith.science/api/pith-number/7PWO22UI74GVXIHXNKBSNOPD6C/graph.json","fetch_events":"https://pith.science/api/pith-number/7PWO22UI74GVXIHXNKBSNOPD6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C/action/storage_attestation","attest_author":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C/action/author_attestation","sign_citation":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C/action/citation_signature","submit_replication":"https://pith.science/pith/7PWO22UI74GVXIHXNKBSNOPD6C/action/replication_record"}},"created_at":"2026-05-19T11:18:05.504001+00:00","updated_at":"2026-05-19T11:18:05.504001+00:00"}