{"id":"W2276221726","doi":"10.1002/2015wr016959","title":"Bootstrap rank‐ordered conditional mutual information (broCMI): A nonlinear input variable selection method for water resources modeling","year":2016,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Mutual information; Feature selection; Selection (genetic algorithm); Rank (graph theory); Nonparametric statistics; Variable (mathematics); Estimator; Parametric statistics; Mathematics; Kernel (algebra); Computer science; Data mining; Mathematical optimization; Statistics; 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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003571223,0.0002366291,0.0002496658,0.0002625104,0.0008977869,0.0002517246,0.0004960865,0.0002592095,0.002637964],"category_scores_gemma":[0.0003656853,0.0001234099,0.00009816641,0.0002919342,0.0003380998,0.0007463978,0.0004762808,0.0003973775,0.001445721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002878743,"about_ca_system_score_gemma":0.00001343087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006645159,"about_ca_topic_score_gemma":0.00003655797,"domain_scores_codex":[0.9960086,0.000518063,0.0005249782,0.0005383221,0.001168159,0.001241888],"domain_scores_gemma":[0.9989696,0.0003386693,0.00005191368,0.0002779203,0.0001459815,0.0002159187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001850399,0.0002345215,0.00160003,0.0001158639,0.0001001995,0.000006079835,0.01241456,0.4394292,0.5264231,0.0001248808,0.003707327,0.01399385],"study_design_scores_gemma":[0.001292671,0.0004206695,0.00005584936,0.00004306087,0.00001293035,0.00002395503,0.00006931583,0.5906819,0.0502755,0.007742576,0.3490865,0.0002950976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8488287,0.000004368895,0.1464494,0.001440868,0.0000491771,0.0006074019,0.0000530757,0.0001360287,0.002430962],"genre_scores_gemma":[0.955658,0.000002887928,0.04003443,0.0002485673,0.0002821654,0.00022709,0.0001704747,0.00004095736,0.003335484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4761476,"threshold_uncertainty_score":0.9993318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06181744656260131,"score_gpt":0.3342697201069468,"score_spread":0.2724522735443455,"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."}}