{"id":"W3011819927","doi":"10.1142/s0218488520500087","title":"Estimating and Controlling Overlap in Gaussian Mixtures for Clustering Methods Evaluation","year":2020,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Mixture model; Set (abstract data type); Artificial intelligence; Data set; Machine learning; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.002688438,0.0001588064,0.0003729646,0.0002921431,0.00007971848,0.0003683765,0.0005308116,0.00006319893,0.000001204232],"category_scores_gemma":[0.001229527,0.0001333936,0.00007215147,0.0002041688,0.00004480786,0.0004225421,0.0001440055,0.0002063186,3.492242e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001848347,"about_ca_system_score_gemma":0.0002642497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004259405,"about_ca_topic_score_gemma":0.00002033232,"domain_scores_codex":[0.9979898,0.0003464424,0.0006678865,0.0002850915,0.0005003907,0.0002103569],"domain_scores_gemma":[0.9971353,0.0009476047,0.0003971138,0.0001048537,0.001252485,0.0001626269],"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":[0.0003330014,0.00005066183,0.0005832952,0.0003021998,0.00009394102,0.0000280576,0.00155102,0.7344235,0.004616914,0.001003475,0.00001660581,0.2569973],"study_design_scores_gemma":[0.003288782,0.0001666081,0.0002364862,0.0004991713,0.0000124762,0.00005570795,0.0002043697,0.9942965,0.0002003028,0.0005829287,0.0003235823,0.0001330842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01016219,0.002356111,0.9839873,0.001586466,0.001472794,0.0003534278,0.000005965132,0.00001701444,0.0000587875],"genre_scores_gemma":[0.8507205,0.00001279802,0.1485462,0.00007347985,0.00059054,0.00003684393,0.000002445783,0.00001183038,0.000005419611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8405582,"threshold_uncertainty_score":0.5439631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05904577131457585,"score_gpt":0.4037623164225094,"score_spread":0.3447165451079335,"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."}}