{"id":"W4246229938","doi":"10.22541/au.163251902.21099343/v1","title":"Learning from mistakes - Assessing the performance and uncertainty in process-based models","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; BGC Engineering (Canada)","funders":"","keywords":"Process (computing); Computer science; Basis (linear algebra); Cluster analysis; Variable (mathematics); Errors-in-variables models; Set (abstract data type); Process modeling; Data mining; Principal component analysis; Machine learning; Artificial intelligence; Mathematics; Work in process; Engineering","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":[0.0005010215,0.0002228244,0.00024097,0.00002057662,0.0002119744,0.0003031901,0.0003067024,0.0002004346,0.0005992948],"category_scores_gemma":[0.0001387314,0.000147286,0.00004066998,0.000148812,0.0002785193,0.0001740455,0.0003861843,0.001015986,0.000008305424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001490631,"about_ca_system_score_gemma":0.00005389098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002722214,"about_ca_topic_score_gemma":0.0003420744,"domain_scores_codex":[0.9983451,0.0001700982,0.0002506488,0.000632495,0.0003187084,0.0002829325],"domain_scores_gemma":[0.9993298,0.0002087703,0.0001298946,0.0002641336,0.000009935557,0.00005743869],"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":[0.000003649267,0.00002302508,0.05670067,0.00002636153,0.000003178959,0.000006573814,0.0007943314,0.9384894,0.0001816463,9.473065e-7,0.000005244415,0.003764983],"study_design_scores_gemma":[0.0001112705,0.00001781699,0.01977891,0.0002017319,0.000009927849,0.00000117938,0.0002766704,0.9783681,0.0001741558,0.0008266271,0.00003346557,0.0002001466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893802,0.00005738102,0.001334134,0.0003988946,0.00005580265,0.0001551055,0.000001367231,0.00007255928,0.008544591],"genre_scores_gemma":[0.9969437,0.00001027928,0.002493165,0.000318098,0.00002073336,0.00002542189,0.00003274973,0.00001560631,0.0001403215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03987871,"threshold_uncertainty_score":0.6561859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04249601030279104,"score_gpt":0.2754217843308965,"score_spread":0.2329257740281054,"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."}}