{"id":"W2121141437","doi":"10.1175/waf884.1","title":"Alternatives to the Chi-Square Test for Evaluating Rank Histograms from Ensemble Forecasts","year":2005,"lang":"en","type":"article","venue":"Weather and Forecasting","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Simon Fraser University","keywords":"Histogram; Rank (graph theory); Mathematics; Statistics; Statistical hypothesis testing; Econometrics; Artificial intelligence; Computer science; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002532698,0.0002229735,0.0002892849,0.0001170689,0.0007458444,0.0003561977,0.0006593839,0.00006871972,0.0001007501],"category_scores_gemma":[0.003891003,0.0001394979,0.000152201,0.0004152799,0.00008852137,0.000182645,0.0002074323,0.0001462952,0.00005354969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004413135,"about_ca_system_score_gemma":0.00002705096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001665832,"about_ca_topic_score_gemma":0.0004364563,"domain_scores_codex":[0.9976441,0.00006922308,0.0006502468,0.0006395954,0.0005991876,0.0003976787],"domain_scores_gemma":[0.9954261,0.003302077,0.0002960564,0.0005444625,0.0002924935,0.0001388694],"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":[0.00002978888,0.00004000886,0.003777865,0.000003101138,0.00001160675,3.197964e-7,0.002492093,0.0004847805,0.001428484,0.001139987,0.003824159,0.9867678],"study_design_scores_gemma":[0.001062842,0.0006307725,0.00597923,0.0001731129,0.00005906553,0.00003129696,0.001618096,0.6661225,0.003017212,0.06792189,0.2527633,0.0006206259],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6217141,0.0004540306,0.360691,0.004879436,0.000179363,0.001603902,0.0002034791,0.0001968867,0.01007772],"genre_scores_gemma":[0.8552596,0.000004438144,0.1417633,0.0004602647,0.0005509119,0.000327727,0.0000112689,0.00003232761,0.001590162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9861472,"threshold_uncertainty_score":0.5736508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2340837015960262,"score_gpt":0.4178356942781782,"score_spread":0.183751992682152,"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."}}