{"id":"W4302316314","doi":"10.48550/arxiv.1408.2128","title":"High-dimensional unsupervised classification via parsimonious\\n contaminated mixtures","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canada Research Chairs","keywords":"Mixture model; Gaussian; Expectation–maximization algorithm; Dimensionality reduction; Generalization; Covariance; Computer science; Context (archaeology); Mathematics; Mixture distribution; Algorithm; Pattern recognition (psychology); Artificial intelligence; Statistics; Probability density function; Maximum likelihood","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005739887,0.0004899217,0.0005683768,0.0003033042,0.00022539,0.0001438947,0.002026964,0.0006373586,0.00003531472],"category_scores_gemma":[0.00003743072,0.0005187056,0.0002747514,0.0004804079,0.0001473092,0.0002887365,0.001253786,0.0007924773,0.00009454737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001900715,"about_ca_system_score_gemma":0.0002027257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002183465,"about_ca_topic_score_gemma":0.00002105888,"domain_scores_codex":[0.9967756,0.0006310132,0.00032763,0.001621485,0.0001751289,0.0004692036],"domain_scores_gemma":[0.9970359,0.0002026521,0.0003656611,0.001791468,0.0003274528,0.00027692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008513148,0.0002637946,0.0003741861,0.0001318297,0.0002434552,0.0002926012,0.0002329531,0.03582375,0.003019893,0.9316798,0.002395398,0.0254572],"study_design_scores_gemma":[0.0006502297,0.00005641827,0.001768255,0.00007294432,0.00008177291,0.000006563832,0.000003601645,0.7757185,0.0009793829,0.2197993,0.0002961749,0.0005668209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09592704,0.00008098806,0.9012175,0.0003318437,0.001043178,0.0003479685,0.00001389139,0.0003567435,0.0006808338],"genre_scores_gemma":[0.9250023,0.00005023602,0.07335556,0.0004257171,0.0001253912,0.000002471013,0.00007216482,0.00002889416,0.0009373123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8290752,"threshold_uncertainty_score":0.9997265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05581815113066747,"score_gpt":0.1973275511852578,"score_spread":0.1415094000545903,"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."}}