{"id":"W4322010848","doi":"10.5194/egusphere-egu23-9520","title":"Estimating the significance of the added skill from initializations: The case of decadal predictions","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Climate variability and models","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ouranos","funders":"","keywords":"Initialization; Null hypothesis; Statistics; Statistic; Econometrics; Contrast (vision); Simple (philosophy); Alternative hypothesis; Mathematics; Statistical hypothesis testing; Test statistic; Computer science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.02640756,0.0006772375,0.0008082438,0.001125856,0.0004619529,0.002133197,0.0007806427,0.001452798,0.001246743],"category_scores_gemma":[0.1886488,0.0003873415,0.001049492,0.001049824,0.003006233,0.002759679,0.001661421,0.002516876,0.0001894298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006396329,"about_ca_system_score_gemma":0.0008866742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002547188,"about_ca_topic_score_gemma":0.001677998,"domain_scores_codex":[0.9929886,0.004225201,0.0004650256,0.001053916,0.0009489265,0.000318393],"domain_scores_gemma":[0.618584,0.3458669,0.01027047,0.01875839,0.004741588,0.001778463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005760683,0.0004543129,0.4645784,0.0006089736,0.002463576,0.0008844397,0.001513485,0.3877675,0.01368186,0.0202987,0.001681253,0.1003069],"study_design_scores_gemma":[0.0002512708,0.001230747,0.3613165,0.0002239955,0.0006606298,0.0002662382,0.0006525784,0.5663807,0.03295959,0.03425165,0.001582542,0.0002234629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.937241,0.0003955886,0.05903459,0.0003802927,0.00008711361,0.00004990786,0.000426375,0.000226583,0.002158516],"genre_scores_gemma":[0.9929237,0.00007717639,0.00630386,0.00006095444,0.00002944645,0.00002509949,0.0003483464,0.00006538815,0.000166103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02640756,"threshold_uncertainty_score":0.1396582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05080271823569973,"score_gpt":0.2923576207325154,"score_spread":0.2415549024968156,"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."}}