{"id":"W4283366791","doi":"10.1029/2021wr031523","title":"Time to Update the Split‐Sample Approach in Hydrological Model Calibration","year":2022,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":221,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Calibration; Computer science; Sample (material); Robustness (evolution); Decision tree; Data mining; Hydrological modelling; Statistics; 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":[0.02602108,0.0005768288,0.0008782814,0.0007950842,0.000849958,0.001705495,0.002018305,0.001122109,0.005128585],"category_scores_gemma":[0.1023935,0.0007536127,0.0007765353,0.0008205266,0.000903232,0.004613862,0.002430921,0.002588056,0.000603659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001085042,"about_ca_system_score_gemma":0.002154116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004324433,"about_ca_topic_score_gemma":0.006303833,"domain_scores_codex":[0.9938992,0.00396945,0.0003276373,0.0006609045,0.0009429977,0.0001998321],"domain_scores_gemma":[0.9277816,0.05505454,0.002763938,0.007029539,0.006546183,0.0008242236],"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":[0.002163254,0.0008362532,0.06674767,0.0003492877,0.0004609819,0.0002311542,0.001175982,0.5143002,0.006829744,0.01983937,0.005804045,0.3812621],"study_design_scores_gemma":[0.0001694653,0.0005231122,0.00938928,0.00008263697,0.00008510677,0.0000537925,0.0003975762,0.9674962,0.005769186,0.01244107,0.003543769,0.00004883432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4123795,0.0005049085,0.5772166,0.00170675,0.0002113883,0.0005092545,0.0005233182,0.001637544,0.005310731],"genre_scores_gemma":[0.8568998,0.00007613214,0.140928,0.0002681754,0.00004130226,0.0003289813,0.0005963369,0.000226674,0.0006345843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02602108,"threshold_uncertainty_score":0.1376143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04327461884392714,"score_gpt":0.2783297328831461,"score_spread":0.235055114039219,"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."}}