{"id":"W2181737587","doi":"","title":"Multivariate Data Cleaning and Classification","year":2011,"lang":"en","type":"article","venue":"","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Data mining; Mahalanobis distance; Computer science; Cluster analysis; Geologist; Multivariate statistics; Range (aeronautics); Data type; Artificial intelligence; Machine learning; Geology; Engineering","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":[0.008350964,0.001915014,0.002397515,0.005905938,0.001920213,0.004411192,0.002516956,0.001365029,0.007156186],"category_scores_gemma":[0.03368272,0.0006522487,0.002973683,0.007044637,0.00135625,0.002347846,0.004386668,0.002636608,0.008363692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000895375,"about_ca_system_score_gemma":0.003597528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003539855,"about_ca_topic_score_gemma":0.002281927,"domain_scores_codex":[0.9892046,0.001721897,0.001742284,0.002790577,0.003996012,0.000544641],"domain_scores_gemma":[0.9798449,0.003703399,0.001368753,0.008203439,0.006699249,0.0001803362],"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":[0.0002948808,0.0001651105,0.00859556,0.001686779,0.0002628957,0.0002982748,0.001055204,0.01101464,0.01641222,0.01348748,0.05327768,0.8934492],"study_design_scores_gemma":[0.0001034017,0.0003675505,0.04046474,0.001008947,0.0003804204,0.001281437,0.00186111,0.1853345,0.1133398,0.07151076,0.5838439,0.0005034097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01110428,0.0006494805,0.9611797,0.0006099429,0.0005158759,0.001193637,0.01180367,0.009858838,0.003084627],"genre_scores_gemma":[0.05107843,0.001201693,0.9082488,0.0003990003,0.0003154652,0.002563518,0.02948537,0.002141384,0.004566251],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008350964,"threshold_uncertainty_score":0.04416466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1785560108601502,"score_gpt":0.2746652647971414,"score_spread":0.09610925393699127,"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."}}