{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002701674,0.00009469267,0.0001117922,0.0001101704,0.0009349645,0.00004232023,0.0006915203,0.00003404239,0.004775063],"category_scores_gemma":[0.0000262639,0.0000533991,0.00002936425,0.0003615715,0.0003584783,0.00008247826,0.00355437,0.0004495276,0.001455202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221269,"about_ca_system_score_gemma":0.000001922159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003456843,"about_ca_topic_score_gemma":0.00002497333,"domain_scores_codex":[0.9974548,0.0006966225,0.0001551347,0.0004168355,0.000654171,0.0006224366],"domain_scores_gemma":[0.9995381,0.00007560048,0.00001080153,0.0003113706,0.000003287004,0.00006090521],"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":[0.0001600609,0.0001293834,0.007216298,0.000003480737,0.00001026322,0.00001171643,0.008320325,0.9723008,0.0008200915,0.0001310778,0.01056722,0.0003292369],"study_design_scores_gemma":[0.0002226882,0.0001487181,0.002073254,7.515886e-7,0.000003211415,0.000002259225,0.0004180337,0.8173074,0.0001917905,0.006640467,0.1728533,0.0001380702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712219,0.000009083437,0.0003268735,0.0134852,0.000008847857,0.0005197176,0.000007409479,0.00002829534,0.01439267],"genre_scores_gemma":[0.9918156,0.000002756088,0.0002871353,0.001032911,0.00001836918,0.0004630539,0.00002758858,0.00001030413,0.006342242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1622861,"threshold_uncertainty_score":0.9993223,"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."}}