{"id":"W4221055148","doi":"10.5194/egusphere-egu22-10846","title":"Time to Update the Split Sample Approach to Hydrological Model Calibration: A Massive Empirical Study","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Calibration; Sample (material); Robustness (evolution); Computer science; Model validation; Hydrological modelling; Statistics; Mathematics; Climatology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03102109,0.0004748269,0.0006141174,0.0007262293,0.0007202805,0.001305178,0.001832256,0.001052541,0.00254808],"category_scores_gemma":[0.1609461,0.0004709396,0.0009623945,0.001025952,0.001431187,0.005142272,0.0018638,0.002488632,0.0002540222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00129533,"about_ca_system_score_gemma":0.001016568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005111292,"about_ca_topic_score_gemma":0.003916838,"domain_scores_codex":[0.9916918,0.005921647,0.0003515813,0.0009387209,0.0009141753,0.0001820059],"domain_scores_gemma":[0.8111216,0.1605464,0.00609287,0.01556085,0.005960559,0.0007176707],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002019559,0.002714001,0.2748857,0.0004405238,0.0007969605,0.0005110738,0.002401339,0.4167126,0.002533193,0.04882823,0.007066812,0.2410899],"study_design_scores_gemma":[0.0001698786,0.0009152491,0.03063305,0.00007528518,0.0001311494,0.00008599773,0.000737593,0.945987,0.00180892,0.01608981,0.003306632,0.00005951375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.872169,0.0005546579,0.1222236,0.001290019,0.00007205861,0.0002498618,0.0003654995,0.0002042121,0.002871163],"genre_scores_gemma":[0.9665422,0.0001339135,0.03207266,0.0001585332,0.00003902859,0.0001466758,0.0004546907,0.00005677934,0.0003955797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9689789,"threshold_uncertainty_score":0.1640571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04134948241100306,"score_gpt":0.2785553029163159,"score_spread":0.2372058205053129,"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."}}