{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007309515,0.001023024,0.001364003,0.004274519,0.0004273867,0.001341766,0.001089529,0.001010925,0.0008739471],"category_scores_gemma":[0.0145115,0.0002724345,0.00127337,0.004507269,0.0002577748,0.002217918,0.0007041513,0.0009827,0.0002918841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001212398,"about_ca_system_score_gemma":0.001118954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006681898,"about_ca_topic_score_gemma":0.004145139,"domain_scores_codex":[0.9972947,0.0009845704,0.0003263918,0.0003236594,0.0009506541,0.000120064],"domain_scores_gemma":[0.9861695,0.01097117,0.0003896976,0.0005752724,0.001784779,0.0001095975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004940244,0.0005362462,0.02499148,0.0006992375,0.0005456995,0.00009180935,0.0001063438,0.3706862,0.0007399904,0.004893007,0.003854863,0.5923612],"study_design_scores_gemma":[0.00002054969,0.0002021027,0.005885327,0.00008388026,0.0001018573,0.00008042534,0.0001030704,0.987636,0.001187336,0.002503372,0.002178443,0.00001765654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4063534,0.06063368,0.5087382,0.003470901,0.0004505696,0.0005174768,0.002104068,0.001984306,0.01574737],"genre_scores_gemma":[0.7588422,0.01527266,0.2214936,0.0002409094,0.0001374484,0.0002239163,0.002401,0.00008991864,0.001298377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007309515,"threshold_uncertainty_score":0.03865683,"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."}}