{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003947416,0.00268669,0.0009337594,0.003557411,0.001087075,0.001666175,0.001913822,0.002940618,0.007462325],"category_scores_gemma":[0.01651094,0.0003224488,0.001573858,0.002169865,0.0006765286,0.003470199,0.002594215,0.002972089,0.008228483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001176782,"about_ca_system_score_gemma":0.00110514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01047933,"about_ca_topic_score_gemma":0.01328476,"domain_scores_codex":[0.9969023,0.001170668,0.0003315476,0.0008566793,0.0004995441,0.0002392087],"domain_scores_gemma":[0.9878978,0.007677812,0.0005568959,0.001559462,0.001531979,0.0007759113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005101387,0.007881488,0.0723671,0.004509503,0.0009783925,0.001747472,0.002309419,0.04836131,0.02670886,0.004196602,0.3789398,0.4468987],"study_design_scores_gemma":[0.0009380828,0.002905308,0.1148809,0.000458877,0.0003852319,0.002371604,0.004808662,0.698428,0.04737956,0.01457403,0.1125982,0.000271671],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.7597936,0.004450578,0.05482153,0.002732928,0.001112082,0.001716632,0.1184292,0.03413029,0.02281314],"genre_scores_gemma":[0.5458922,0.0006510656,0.07759377,0.00118113,0.0003391301,0.001377833,0.3567173,0.001279728,0.0149678],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01047933,"threshold_uncertainty_score":0.02496397,"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."}}