{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002318653,0.00007658484,0.00008182658,0.000007157892,0.0001766183,0.00008216631,0.00009135519,0.00003983852,0.0005746089],"category_scores_gemma":[0.0001026662,0.00004855974,0.00001283205,0.0001779109,0.0001442528,0.0001821047,0.00004362053,0.0001961959,0.00001539799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004670395,"about_ca_system_score_gemma":0.0000172948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004110955,"about_ca_topic_score_gemma":0.0001603207,"domain_scores_codex":[0.9992349,0.00007619613,0.0001110392,0.0002428083,0.0001605058,0.0001745589],"domain_scores_gemma":[0.9996833,0.0001459467,0.00003241974,0.00009871081,0.000005438982,0.00003421944],"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":[0.000002190869,0.00001504034,0.1002028,0.000003138215,7.911696e-7,0.000005331732,0.0003116688,0.8939762,0.001231077,0.000004610555,0.000006998967,0.00424017],"study_design_scores_gemma":[0.0001235278,0.00001669537,0.02989785,0.00002439089,0.000002679304,0.000001863966,0.0001973055,0.9677719,0.001004072,0.0007505087,0.0001324975,0.00007668477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851668,0.00002091019,0.0006099967,0.0005288973,0.00001395464,0.00003926569,3.254222e-7,0.00003587519,0.0135839],"genre_scores_gemma":[0.99797,0.00000237169,0.001314883,0.0004432938,0.000008123694,0.000004420935,0.000004040279,0.000005422349,0.0002474887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07379574,"threshold_uncertainty_score":0.6291565,"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."}}