{"id":"W4375869758","doi":"10.48550/arxiv.1907.01136","title":"Finding Outliers in Gaussian Model-Based Clustering","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Outlier; Cluster analysis; Gaussian; Computer science; Mixture model; Pattern recognition (psychology); Artificial intelligence; Statistics; Econometrics; Mathematics; Data mining; Physics","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":[0.0004154032,0.0004022283,0.0004462003,0.0008734269,0.0001214005,0.0001903195,0.003039481,0.000359072,0.00000987588],"category_scores_gemma":[0.00004877003,0.0005070314,0.0001839433,0.0008712932,0.00009608081,0.0005161362,0.004231671,0.001269798,0.0001000901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028428,"about_ca_system_score_gemma":0.0005089207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001147235,"about_ca_topic_score_gemma":0.00009395246,"domain_scores_codex":[0.9969784,0.0001473575,0.0002713679,0.001603596,0.0002060842,0.0007931829],"domain_scores_gemma":[0.9975037,0.0001339699,0.0001961649,0.001850917,0.00009190318,0.0002233356],"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":[0.00002387364,0.00004066781,0.001007144,0.0001381818,0.00001639204,0.0003496586,0.0002231544,0.993827,0.00002698496,0.003106548,0.00001294608,0.001227453],"study_design_scores_gemma":[0.0007371702,0.00003311237,0.0003330953,0.0002521559,0.000007550014,0.000002145719,0.00004935201,0.9915909,0.00007993886,0.006362567,0.00003596559,0.0005160319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05300874,0.00002409813,0.9434557,0.0001163244,0.0004862038,0.0004320319,0.000009545909,0.0002494962,0.002217878],"genre_scores_gemma":[0.9643716,0.00002742717,0.03353868,0.00007448226,0.00003277198,0.000002638702,0.000008808257,0.00003934863,0.001904286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9113628,"threshold_uncertainty_score":0.9997382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1026567429127034,"score_gpt":0.2399083167034491,"score_spread":0.1372515737907457,"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."}}