{"id":"W4389523781","doi":"10.18653/v1/2023.emnlp-main.99","title":"Evaluating Cross-Domain Text-to-SQL Models and Benchmarks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); SQL; Ranking (information retrieval); Field (mathematics); Query by Example; Domain (mathematical analysis); Matching (statistics); Information retrieval; Programming language; Data mining; Web search query; Search engine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007282724,0.0001047447,0.0001249269,0.00009153969,0.000203169,0.0001279698,0.0002321821,0.00002910796,0.00002555083],"category_scores_gemma":[0.00007147552,0.00008611977,0.00002247883,0.0004671915,0.00003429729,0.0009420576,0.0006114011,0.00005839451,0.00007735258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001461111,"about_ca_system_score_gemma":0.00003940082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004863236,"about_ca_topic_score_gemma":0.00003106084,"domain_scores_codex":[0.9987558,0.00003753968,0.0001926571,0.000402361,0.0003301817,0.000281457],"domain_scores_gemma":[0.9992301,0.0001042787,0.00003577285,0.0004480009,0.00006276984,0.000119066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004735254,0.000007984191,0.0003481062,0.00002816696,0.000007951228,0.00001860471,0.00142984,0.0147127,0.004488212,0.9398001,0.002627919,0.03652565],"study_design_scores_gemma":[0.0003645137,0.0001120476,0.002910577,0.00005027136,0.000001632112,0.00002276151,0.000254765,0.9366407,0.0007940518,0.04391808,0.01459088,0.0003397425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09424818,0.00004427645,0.8940883,0.0004455182,0.0001673438,0.0001669132,0.000009171107,0.0002390509,0.0105913],"genre_scores_gemma":[0.3238245,0.00001051678,0.6733562,0.0004347926,0.00008052401,0.00005525412,0.00001324432,0.00001200636,0.00221302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.921928,"threshold_uncertainty_score":0.3511862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07326356775616878,"score_gpt":0.3835356209260535,"score_spread":0.3102720531698847,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}