{"id":"W4307948995","doi":"10.3390/forecast4040048","title":"Precision and Reliability of Forecasts Performance Metrics","year":2022,"lang":"en","type":"article","venue":"Forecasting","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Mitacs","keywords":"Variance (accounting); Reliability (semiconductor); Metric (unit); Computer science; Sensitivity (control systems); Noise (video); Series (stratigraphy); Selection (genetic algorithm); Econometrics; Quality (philosophy); Model selection; Performance metric; Statistics; Data mining; Reliability engineering; Machine learning; Artificial intelligence; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005150333,0.0001154068,0.0002519431,0.0003496595,0.0005695967,0.00005167901,0.0006045726,0.00003695069,0.0002411966],"category_scores_gemma":[0.004104905,0.00009469515,0.0000797851,0.001943413,0.0001160479,0.0002006915,0.0009337938,0.0002303377,0.000004766511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005344609,"about_ca_system_score_gemma":0.00004178729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002927261,"about_ca_topic_score_gemma":0.000002067811,"domain_scores_codex":[0.9973661,0.0001187784,0.0007386925,0.0004549571,0.001092452,0.0002290355],"domain_scores_gemma":[0.99699,0.001597633,0.0004722043,0.0005761017,0.0002894411,0.00007460524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006636279,0.0001101899,0.1044833,0.00002720088,0.000004024857,0.000001690635,0.0006498549,0.005824041,0.000285515,0.001802115,0.004252125,0.8824936],"study_design_scores_gemma":[0.0003164255,0.0006991255,0.02019013,0.00003072334,0.00001580872,0.0001175669,0.0005343754,0.8800499,0.002496979,0.0521656,0.04310712,0.0002762427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848043,0.00006285482,0.009125797,0.0001404454,0.0001190846,0.0002854944,0.00004178791,0.00006253129,0.005357681],"genre_scores_gemma":[0.9658207,0.000006649973,0.03360845,0.00002600401,0.00002745069,0.0000688327,0.000004794079,0.00001237264,0.0004247217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8822173,"threshold_uncertainty_score":0.4914251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1467905736224284,"score_gpt":0.3568156231551683,"score_spread":0.2100250495327398,"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."}}