{"id":"W2798242991","doi":"10.1007/s00477-018-1539-8","title":"Statistics for sample splitting for the calibration and validation of hydrological models","year":2018,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Guangzhou Municipal Science and Technology Project; National Natural Science Foundation of China","keywords":"Goodness of fit; Calibration; Reliability (semiconductor); Statistics; Sample size determination; Sample (material); Statistical hypothesis testing; Computer science; Range (aeronautics); Population; Statistical model; Data mining; 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":[],"consensus_categories":[],"category_scores_codex":[0.00116882,0.00008781967,0.0001070264,0.00002516535,0.0008344872,0.00002296687,0.00008859161,0.00004125276,0.00006056923],"category_scores_gemma":[0.0001274491,0.00005782837,0.00001706457,0.0000369375,0.001291473,0.0001123418,0.0002915811,0.00009591865,0.000001418578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005160347,"about_ca_system_score_gemma":0.000004450224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001340391,"about_ca_topic_score_gemma":0.00003803861,"domain_scores_codex":[0.9989657,0.00007611402,0.0001663144,0.0002682452,0.0002521884,0.0002714265],"domain_scores_gemma":[0.9982003,0.001556393,0.00006786626,0.000114905,0.000007009595,0.00005350253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003333188,0.002173281,0.5330468,0.0003653576,0.00123005,0.000003163906,0.009121153,0.1465366,0.0140275,0.09993237,0.007282034,0.1829484],"study_design_scores_gemma":[0.0007756483,0.001992243,0.02849219,0.000006482473,0.0000703324,7.913006e-7,0.000631362,0.7791988,0.0005176217,0.1879078,0.0002966562,0.0001100694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2845997,0.00003670129,0.7140306,0.0002550707,0.00002431803,0.0008006184,0.0001945163,0.000004056689,0.00005444014],"genre_scores_gemma":[0.9783183,0.000294136,0.02097092,0.00002521779,0.00004126424,0.0002349594,0.00003878786,0.000007240631,0.00006922646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6937186,"threshold_uncertainty_score":0.6418285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0499276736545958,"score_gpt":0.3455323242670152,"score_spread":0.2956046506124194,"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."}}