{"id":"W4200584175","doi":"10.1061/(asce)wr.1943-5452.0001512","title":"Data Mining Algorithms for Water Main Condition Prediction—Comparative Analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Water Resources Planning and Management","topic":"Water Systems and Optimization","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Hyperparameter; Decision tree; Computer science; Data mining; Sensitivity (control systems); Machine learning; Support vector machine; AdaBoost; Set (abstract data type); Random forest; Process (computing); Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003688965,0.00009884331,0.0002320502,0.0002305233,0.00008587579,0.0001364437,0.00010784,0.00003261124,0.0000149305],"category_scores_gemma":[0.000001595697,0.00006291676,0.00005312769,0.00007887297,0.00001008634,0.0002195879,0.00007384409,0.00005586143,9.552843e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002172692,"about_ca_system_score_gemma":0.000001210813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001599709,"about_ca_topic_score_gemma":0.000005471467,"domain_scores_codex":[0.999188,0.00002942838,0.0003453359,0.0001337573,0.0001418583,0.0001615864],"domain_scores_gemma":[0.9996864,0.00001433346,0.00005038067,0.0001469282,0.00005300761,0.00004898184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003584296,0.00002405917,0.001165369,0.0002722598,0.003153536,0.0001410141,0.01394159,0.9583849,0.0005416437,0.000007983854,0.02185734,0.0004744486],"study_design_scores_gemma":[0.00144868,0.0001239366,0.002599943,0.0002753086,0.001870837,0.0001218239,0.00658762,0.5803257,0.009929762,0.0000528422,0.3963866,0.0002769671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6500295,0.0008446186,0.3465086,0.0001908783,0.0005267755,0.0001903694,0.0001601862,0.00005414122,0.001494914],"genre_scores_gemma":[0.9841285,0.00006344161,0.01327951,0.00002808291,0.0002898476,0.00001253145,0.0006603769,0.0000136008,0.001524077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3780592,"threshold_uncertainty_score":0.2565671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04079785253270803,"score_gpt":0.2696802578852627,"score_spread":0.2288824053525547,"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."}}