{"id":"W2806096886","doi":"10.1016/j.csda.2018.05.015","title":"Addressing overfitting and underfitting in Gaussian model-based clustering","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Overfitting; Cluster analysis; Maxima and minima; Mixture model; Expectation–maximization algorithm; Context (archaeology); Maxima; Computer science; Nonparametric statistics; Artificial intelligence; Convergence (economics); Machine learning; Gaussian; Mathematics; Mathematical optimization; Algorithm; Pattern recognition (psychology); Artificial neural network; Econometrics; Maximum likelihood; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0009871016,0.000168046,0.0002976695,0.0004218596,0.0002713411,0.0004017929,0.0006840586,0.00005341592,0.00000978838],"category_scores_gemma":[0.0001937301,0.0001743691,0.00003292449,0.00113256,0.0001101483,0.0004920881,0.0006616972,0.0001466566,0.000002925588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000493506,"about_ca_system_score_gemma":0.0001437919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000147844,"about_ca_topic_score_gemma":0.0004597765,"domain_scores_codex":[0.9980463,0.0001630573,0.0004311899,0.0007338703,0.0003386863,0.0002869104],"domain_scores_gemma":[0.998386,0.0005060731,0.0001885666,0.0006606734,0.0001450014,0.0001136765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001099856,0.00006291414,0.005947079,0.00005940567,0.0002444319,0.00003191044,0.0007031336,0.6498353,0.00002602923,0.1398163,0.0004179289,0.2028446],"study_design_scores_gemma":[0.000231278,0.00001319203,0.007734825,0.00003353955,0.0001149955,0.000002175183,0.000005061083,0.9112561,0.000004176133,0.08040269,0.00002082042,0.0001810912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007151477,0.00006867974,0.9983868,0.0002185693,0.00005461393,0.00006556698,0.0002467532,0.00004510973,0.0001987753],"genre_scores_gemma":[0.3880886,0.00000273913,0.6113294,0.0002563797,0.0000379042,0.000001553768,0.0002683908,0.000006977381,0.000008120202],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3873734,"threshold_uncertainty_score":0.7110567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1142948983470015,"score_gpt":0.3791082464019549,"score_spread":0.2648133480549534,"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."}}