{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K3NFCTAL7WGGTQFGBSCDQGYDNG","short_pith_number":"pith:K3NFCTAL","schema_version":"1.0","canonical_sha256":"56da514c0bfd8c69c0a60c84381b0369a441607107a147eef32433a9d1257963","source":{"kind":"arxiv","id":"2410.01066","version":2},"attestation_state":"computed","paper":{"title":"From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Mohammadjafari, Anthony S. Maida, Raju Gottumukkala","submitted_at":"2024-10-01T20:46:25Z","abstract_excerpt":"LLMs when used with Retrieval Augmented Generation (RAG), are greatly improving the SOTA of translating natural language queries to structured and correct SQL. Unlike previous reviews, this survey provides a comprehensive study of the evolution of LLM-based text-to-SQL systems, from early rule-based models to advanced LLM approaches that use (RAG) systems. We discuss benchmarks, evaluation methods, and evaluation metrics. Also, we uniquely study the use of Graph RAGs for better contextual accuracy and schema linking in these systems. Finally, we highlight key challenges such as computational e"},"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":"2410.01066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T20:46:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a8c263f0ae88ee111ee8dfd7d18ac89e176dfdb7b49fde57fd4a068a3938b1d","abstract_canon_sha256":"4b493b4f55a7eac24de9a1b622007481badfe9775aa96b8676280dabb356d5c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:09.619303Z","signature_b64":"BY9BM8AmGiRDaQKvAuTPLafBpOpnJXFYXubCJy4CyXe8ZFxYSfFDQIta6qEjnqf/arCWjYO2vt3Z71DyNseLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56da514c0bfd8c69c0a60c84381b0369a441607107a147eef32433a9d1257963","last_reissued_at":"2026-07-05T10:09:09.618766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:09.618766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Mohammadjafari, Anthony S. Maida, Raju Gottumukkala","submitted_at":"2024-10-01T20:46:25Z","abstract_excerpt":"LLMs when used with Retrieval Augmented Generation (RAG), are greatly improving the SOTA of translating natural language queries to structured and correct SQL. Unlike previous reviews, this survey provides a comprehensive study of the evolution of LLM-based text-to-SQL systems, from early rule-based models to advanced LLM approaches that use (RAG) systems. We discuss benchmarks, evaluation methods, and evaluation metrics. Also, we uniquely study the use of Graph RAGs for better contextual accuracy and schema linking in these systems. Finally, we highlight key challenges such as computational e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01066","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/2410.01066/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":"2410.01066","created_at":"2026-07-05T10:09:09.618843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01066v2","created_at":"2026-07-05T10:09:09.618843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01066","created_at":"2026-07-05T10:09:09.618843+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3NFCTAL7WGG","created_at":"2026-07-05T10:09:09.618843+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3NFCTAL7WGGTQFG","created_at":"2026-07-05T10:09:09.618843+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3NFCTAL","created_at":"2026-07-05T10:09:09.618843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02837","citing_title":"Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23978","citing_title":"LLM Agents Are the Antidote to Walled Gardens","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19010","citing_title":"AgentNLQ: A General-Purpose Agent for Natural Language to SQL","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16493","citing_title":"NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions","ref_index":44,"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":284,"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":299,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG","json":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG.json","graph_json":"https://pith.science/api/pith-number/K3NFCTAL7WGGTQFGBSCDQGYDNG/graph.json","events_json":"https://pith.science/api/pith-number/K3NFCTAL7WGGTQFGBSCDQGYDNG/events.json","paper":"https://pith.science/paper/K3NFCTAL"},"agent_actions":{"view_html":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG","download_json":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG.json","view_paper":"https://pith.science/paper/K3NFCTAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01066&json=true","fetch_graph":"https://pith.science/api/pith-number/K3NFCTAL7WGGTQFGBSCDQGYDNG/graph.json","fetch_events":"https://pith.science/api/pith-number/K3NFCTAL7WGGTQFGBSCDQGYDNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG/action/storage_attestation","attest_author":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG/action/author_attestation","sign_citation":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG/action/citation_signature","submit_replication":"https://pith.science/pith/K3NFCTAL7WGGTQFGBSCDQGYDNG/action/replication_record"}},"created_at":"2026-07-05T10:09:09.618843+00:00","updated_at":"2026-07-05T10:09:09.618843+00:00"}