{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DPG7Z3MS564G6FNKHMEBQDATN5","short_pith_number":"pith:DPG7Z3MS","schema_version":"1.0","canonical_sha256":"1bcdfced92efb86f15aa3b08180c136f63a5267a5d2b3dcd8f22ac8062acf04f","source":{"kind":"arxiv","id":"2404.12560","version":1},"attestation_state":"computed","paper":{"title":"Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Andrew J. Duberstein, Dayton G. Thorpe, Ian A. Kinsey","submitted_at":"2024-04-19T00:48:30Z","abstract_excerpt":"The current state-of-the-art (SOTA) for automated text-to-SQL still falls well short of expert human performance as measured by execution accuracy (EX) on the BIRD-SQL benchmark. The most accurate methods are also slow and expensive. To advance the SOTA for text-to-SQL while reducing cost and improving speed, we explore the combination of low-cost fine tuning, novel methods for diverse retrieval-augmented generation (RAG) and new input and output formats that help large language models (LLMs) achieve higher EX. We introduce two new methods, Dubo-SQL v1 and v2. Dubo-SQL v1 sets a new record for"},"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":"2404.12560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-19T00:48:30Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"b3f9e1a823bb562068883f2cb79140ce0b767620e22433ff1bb41aa62e503a8b","abstract_canon_sha256":"bc1617b74ec605f86cd603fca84936d888cca1b0413b13f49b8ed520944682c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:55.294362Z","signature_b64":"vorbRmy0yNOaProWWZJAaML25LGwsyIZmTnS5tWsF131KTcRQKzAYW+oHeww71G3S2oFNtLz+ix1awTl0V0/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bcdfced92efb86f15aa3b08180c136f63a5267a5d2b3dcd8f22ac8062acf04f","last_reissued_at":"2026-07-05T08:09:55.293828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:55.293828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Andrew J. Duberstein, Dayton G. Thorpe, Ian A. Kinsey","submitted_at":"2024-04-19T00:48:30Z","abstract_excerpt":"The current state-of-the-art (SOTA) for automated text-to-SQL still falls well short of expert human performance as measured by execution accuracy (EX) on the BIRD-SQL benchmark. The most accurate methods are also slow and expensive. To advance the SOTA for text-to-SQL while reducing cost and improving speed, we explore the combination of low-cost fine tuning, novel methods for diverse retrieval-augmented generation (RAG) and new input and output formats that help large language models (LLMs) achieve higher EX. We introduce two new methods, Dubo-SQL v1 and v2. Dubo-SQL v1 sets a new record for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12560","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/2404.12560/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":"2404.12560","created_at":"2026-07-05T08:09:55.293890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12560v1","created_at":"2026-07-05T08:09:55.293890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12560","created_at":"2026-07-05T08:09:55.293890+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPG7Z3MS564G","created_at":"2026-07-05T08:09:55.293890+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPG7Z3MS564G6FNK","created_at":"2026-07-05T08:09:55.293890+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPG7Z3MS","created_at":"2026-07-05T08:09:55.293890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5","json":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5.json","graph_json":"https://pith.science/api/pith-number/DPG7Z3MS564G6FNKHMEBQDATN5/graph.json","events_json":"https://pith.science/api/pith-number/DPG7Z3MS564G6FNKHMEBQDATN5/events.json","paper":"https://pith.science/paper/DPG7Z3MS"},"agent_actions":{"view_html":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5","download_json":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5.json","view_paper":"https://pith.science/paper/DPG7Z3MS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12560&json=true","fetch_graph":"https://pith.science/api/pith-number/DPG7Z3MS564G6FNKHMEBQDATN5/graph.json","fetch_events":"https://pith.science/api/pith-number/DPG7Z3MS564G6FNKHMEBQDATN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5/action/storage_attestation","attest_author":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5/action/author_attestation","sign_citation":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5/action/citation_signature","submit_replication":"https://pith.science/pith/DPG7Z3MS564G6FNKHMEBQDATN5/action/replication_record"}},"created_at":"2026-07-05T08:09:55.293890+00:00","updated_at":"2026-07-05T08:09:55.293890+00:00"}