{"id":"W4287328882","doi":"10.48550/arxiv.2102.06851","title":"Robust Model-Based Clustering","year":2021,"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":"Natural Sciences and Engineering Research Council of Canada; Ministry of Defense; Universidad de Buenos Aires","keywords":"Estimator; Cluster analysis; Computer science; Multivariate statistics; Set (abstract data type); Robust statistics; Data mining; Monte Carlo method; Class (philosophy); Algorithm; Mathematics; Artificial intelligence; Statistics; Machine learning","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":[0.0003426118,0.0003578116,0.0004058491,0.0002118033,0.0001455203,0.0002729979,0.001953398,0.0003828967,0.00001989377],"category_scores_gemma":[0.00002153644,0.000427281,0.0003237322,0.0004634459,0.00006282783,0.0003416905,0.002488244,0.0006983986,0.00001213443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001783204,"about_ca_system_score_gemma":0.0005056218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005118952,"about_ca_topic_score_gemma":0.00004776014,"domain_scores_codex":[0.9976527,0.000220285,0.0001957615,0.00142098,0.0001006478,0.0004095891],"domain_scores_gemma":[0.9975524,0.00006863179,0.0001758635,0.001807872,0.0001752767,0.0002199325],"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":[0.00000665072,0.00004687596,0.00003551173,0.00007719619,0.00003040896,0.0003382357,0.0001100902,0.9341446,0.00003913934,0.0627786,0.00008365545,0.002309009],"study_design_scores_gemma":[0.0002854986,0.00001365895,0.0000249767,0.0001197161,0.0000409539,0.000003699362,0.000009447982,0.9628224,0.000198551,0.0359916,0.0000427255,0.0004467694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008396638,0.00009367532,0.9861414,0.000143126,0.000607651,0.0001797439,0.000006093152,0.0002859386,0.004145762],"genre_scores_gemma":[0.5798534,0.00003547497,0.4189464,0.0002522726,0.00004189308,7.226158e-7,0.000008151127,0.00001701189,0.0008446851],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5714567,"threshold_uncertainty_score":0.9998179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1260493335254669,"score_gpt":0.2006607022520942,"score_spread":0.0746113687266273,"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."}}