{"id":"W2963736043","doi":"10.1016/j.patcog.2019.107031","title":"High-dimensional unsupervised classification via parsimonious contaminated mixtures","year":2019,"lang":"en","type":"preprint","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Mixture model; Gaussian; Expectation–maximization algorithm; Dimensionality reduction; Generalization; Covariance; Context (archaeology); Computer science; Mathematics; Mixture distribution; Maximization; Algorithm; Pattern recognition (psychology); Artificial intelligence; Applied mathematics; Mathematical optimization; Statistics; Probability density function; Maximum likelihood","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006066742,0.0004919361,0.000551159,0.000271079,0.0001160176,0.000275651,0.0008974318,0.0006708845,0.00009035144],"category_scores_gemma":[0.00003613673,0.0004780785,0.0002282061,0.000183282,0.00004534242,0.0002792139,0.0006311519,0.0008610639,0.0004436435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001335429,"about_ca_system_score_gemma":0.0001365021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000261158,"about_ca_topic_score_gemma":0.00001439355,"domain_scores_codex":[0.9966294,0.0005896955,0.0005830843,0.001259611,0.0005121235,0.0004261505],"domain_scores_gemma":[0.9976809,0.0001865925,0.0004623401,0.00110618,0.0004139675,0.0001500035],"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":[0.00001702608,0.0001411297,0.0002306385,0.0001775452,0.00008339062,0.000023333,0.000206875,0.00005947617,0.003976563,0.0001766535,0.001022552,0.9938848],"study_design_scores_gemma":[0.002456402,0.0002758352,0.02664539,0.001198094,0.000244626,0.0000852204,0.00001035314,0.66308,0.0306968,0.2727127,0.0002642769,0.002330297],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07087572,0.0002348428,0.9232146,0.0009973886,0.003087728,0.0008206779,0.00009821283,0.000326533,0.0003443199],"genre_scores_gemma":[0.8460794,0.00007047358,0.1506228,0.001376235,0.000299243,0.0001551413,0.001245014,0.00004603003,0.0001056393],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9915545,"threshold_uncertainty_score":0.9997671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0399435296291964,"score_gpt":0.2662526178915237,"score_spread":0.2263090882623273,"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."}}