{"id":"W3153642306","doi":"10.5194/egusphere-egu21-6312","title":"Learning from mistakes - Assessing the performance and uncertainty in process-based models","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"BGC Engineering (Canada); University of Calgary","funders":"","keywords":"Variable (mathematics); Process (computing); Set (abstract data type); Computer science; Cluster analysis; Field (mathematics); Data mining; Statistics; Mathematics; Artificial intelligence","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":[0.0244316,0.001625903,0.001204591,0.003008585,0.0006897532,0.00309465,0.001681233,0.001622693,0.0007444967],"category_scores_gemma":[0.09266604,0.0005832749,0.001077869,0.001573792,0.001877506,0.003956227,0.003043965,0.001770588,0.0001396944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001926045,"about_ca_system_score_gemma":0.001896025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006354002,"about_ca_topic_score_gemma":0.00357297,"domain_scores_codex":[0.9903089,0.005455242,0.0008964151,0.001134268,0.001882543,0.0003226462],"domain_scores_gemma":[0.8875018,0.09635895,0.006330014,0.004873461,0.004181985,0.0007537029],"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":[0.0001245669,0.00007095809,0.01612221,0.00008601198,0.0001725149,0.0000751655,0.0002948565,0.9448164,0.000355128,0.007542034,0.0001660986,0.03017406],"study_design_scores_gemma":[0.000003669858,0.00005273506,0.001447506,0.00001958024,0.00001480344,0.00001674572,0.00005174403,0.9871932,0.0005307968,0.01056586,0.00008814927,0.00001520235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2639555,0.0003252244,0.7322915,0.0005965931,0.00004145365,0.00015689,0.000212677,0.0004442256,0.001976043],"genre_scores_gemma":[0.9227121,0.0001367599,0.07644082,0.0000490636,0.00002503026,0.00009691837,0.000222463,0.00004954569,0.0002671894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0244316,"threshold_uncertainty_score":0.1292082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03304457753635645,"score_gpt":0.2629414268266119,"score_spread":0.2298968492902554,"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."}}