{"id":"W6912495436","doi":"10.5281/zenodo.3701528","title":"Conquering confounds and covariates in machine learning with the python library confounds","year":2020,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"","field":"","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Python (programming language); Covariate; Random forest; Classifier (UML); Support vector machine; Training set","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":[0.005293326,0.002294019,0.002231204,0.0016149,0.0009807377,0.003782422,0.003569749,0.001610438,0.09354234],"category_scores_gemma":[0.02013973,0.001995703,0.003453115,0.001874516,0.001802181,0.004023227,0.008246843,0.004288013,0.05805861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220988,"about_ca_system_score_gemma":0.003695658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004408778,"about_ca_topic_score_gemma":0.01009383,"domain_scores_codex":[0.9966193,0.001020376,0.0002184636,0.0007443387,0.001043598,0.000353789],"domain_scores_gemma":[0.99417,0.002892061,0.0003941813,0.001683499,0.0005146018,0.0003457556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005608537,0.0002038547,0.004585116,0.0009809919,0.0004675754,0.0003031636,0.0003039967,0.02143716,0.002521005,0.08596068,0.6392249,0.2434508],"study_design_scores_gemma":[0.0004651165,0.00007038212,0.002589443,0.0002690089,0.0001587847,0.0003333768,0.00004358546,0.2571125,0.0097292,0.3212469,0.4077736,0.0002081689],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001589259,0.0004120775,0.6937138,0.001206323,0.0003826866,0.0001464564,0.01664765,0.2751105,0.01079123],"genre_scores_gemma":[0.05721129,0.0009051046,0.7060236,0.002549747,0.000621962,0.001470411,0.04088886,0.1457278,0.04460126],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.09354234,"threshold_uncertainty_score":0.3129303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01904077049953623,"score_gpt":0.2148665636057968,"score_spread":0.1958257931062606,"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."}}