{"id":"W1916284516","doi":"","title":"Robust High-Dimensional Modeling with the Contaminated Gaussian Distribution","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Outlier; Gaussian; Spurious relationship; Mixture model; Gaussian noise; Mathematics; Computer science; Expectation–maximization algorithm; Generalization; Algorithm; Dimension (graph theory); Gaussian network model; Distribution (mathematics); Applied mathematics; Mathematical optimization; Statistics; Mathematical analysis; Physics; Combinatorics; Maximum likelihood","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005398239,0.0003412612,0.000336597,0.00008138265,0.000316979,0.0001478319,0.001450917,0.0002784939,0.000008981345],"category_scores_gemma":[0.00001379794,0.0002486338,0.0001328265,0.0003730949,0.0001204902,0.0002269936,0.001063293,0.0007326812,0.00001697069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001559982,"about_ca_system_score_gemma":0.0001802392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002266425,"about_ca_topic_score_gemma":0.00004932903,"domain_scores_codex":[0.9979414,0.0003596798,0.0001620045,0.001026884,0.0001401819,0.0003698355],"domain_scores_gemma":[0.9980861,0.00009659594,0.0002104981,0.001221101,0.0002327819,0.0001529394],"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":[0.0000219581,0.00002317902,0.00001338758,0.00001392024,0.00004261729,0.00006084544,0.00003957592,0.579998,0.000007528445,0.4187979,0.0001980544,0.0007830901],"study_design_scores_gemma":[0.0003990584,0.00004810554,0.000120431,0.00008610817,0.00007696217,0.00001008075,0.000008297184,0.9488088,0.00004210453,0.04996987,0.00008803861,0.0003421784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06615657,0.00003018844,0.9320081,0.0006631861,0.00029103,0.0002569171,0.00002174861,0.0001712574,0.0004009625],"genre_scores_gemma":[0.9659324,0.00001365083,0.03321167,0.0001852491,0.00007950729,0.000001468494,0.00007356833,0.00001677819,0.0004857451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8997758,"threshold_uncertainty_score":0.9999966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05556797779894152,"score_gpt":0.1764303539580073,"score_spread":0.1208623761590658,"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."}}