{"id":"W3093562467","doi":"10.48550/arxiv.2010.12634","title":"Did You Ask a Good Question? A Cross-Domain Question Intention Classification Benchmark for Text-to-SQL","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Computer science; SQL; Task (project management); Set (abstract data type); Baseline (sea); Domain (mathematical analysis); Test set; Ask price; Null (SQL); Query by Example; Artificial intelligence; Information retrieval; Natural language processing; Data mining; Database; Programming language; Web search query; Search engine; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005957747,0.0003652477,0.0003513948,0.0003454723,0.0002756585,0.0003745329,0.001649192,0.0003953695,0.00001065631],"category_scores_gemma":[0.0001936883,0.0004569497,0.0002446316,0.0006361425,0.00006062849,0.0006297884,0.001262629,0.0005253787,0.00008092444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000584984,"about_ca_system_score_gemma":0.0002042907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002281269,"about_ca_topic_score_gemma":0.00008663783,"domain_scores_codex":[0.9969388,0.0002320187,0.0004113048,0.001854618,0.0001726995,0.0003905546],"domain_scores_gemma":[0.9975091,0.00009850002,0.0004097941,0.001268918,0.000435766,0.0002779221],"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":[0.000095517,0.00014391,0.003833542,0.0001730997,0.00006543598,0.0000284912,0.0006689068,0.09571164,0.0006343504,0.8949625,0.0001964598,0.003486127],"study_design_scores_gemma":[0.0006376255,0.0001444408,0.009570073,0.0002056586,0.00005397697,0.000003528593,0.00009289768,0.823872,0.00006754667,0.1633266,0.001540098,0.0004855614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1808859,0.000020243,0.8150223,0.001089338,0.0008784398,0.0008957611,0.00002155675,0.0003843642,0.0008020646],"genre_scores_gemma":[0.9650194,0.00002527118,0.03350507,0.0001604568,0.0001958352,0.00002172803,0.00008582207,0.00002622226,0.0009601951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7841335,"threshold_uncertainty_score":0.9997882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08798120581144701,"score_gpt":0.2445877155925463,"score_spread":0.1566065097810993,"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."}}