{"id":"W3131740359","doi":"10.1016/j.datak.2021.101876","title":"Generation of Gaussian sets for clustering methods assessment","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Generator (circuit theory); Fuzzy clustering; Curse of dimensionality; Rand index; Mixture model; Data mining; Homogeneity (statistics); Artificial intelligence; Gaussian; Pattern recognition (psychology); Set (abstract data type); Hierarchical clustering; Maximization; Sensitivity (control systems); Algorithm; Machine learning; Mathematics; Mathematical optimization; Power (physics); Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009924402,0.00151307,0.001283073,0.005248564,0.001954774,0.002916367,0.002567967,0.002144465,0.005694978],"category_scores_gemma":[0.04043841,0.0007541541,0.002485624,0.002935671,0.00104456,0.001933597,0.003944206,0.002505636,0.002006472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002120038,"about_ca_system_score_gemma":0.003760818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005646474,"about_ca_topic_score_gemma":0.005863426,"domain_scores_codex":[0.9928108,0.002700549,0.0004044385,0.0008757592,0.002769313,0.0004391466],"domain_scores_gemma":[0.9839677,0.005843,0.0006213317,0.002344047,0.006874896,0.0003490931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000797116,0.0004784135,0.008731701,0.0006865494,0.0003745486,0.0002634869,0.001395655,0.2284048,0.01591539,0.1112095,0.01886415,0.6128789],"study_design_scores_gemma":[0.00007129453,0.0001827875,0.002263007,0.0001266152,0.00007467827,0.0001398023,0.0002228027,0.9240623,0.01514607,0.04927241,0.008371458,0.0000666709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0166258,0.0001336606,0.9788477,0.0001430592,0.00008049722,0.0004186926,0.0003764399,0.001584867,0.001789317],"genre_scores_gemma":[0.1725505,0.0001481566,0.8222083,0.0001000505,0.00003574939,0.0007899234,0.001777781,0.000709928,0.001679479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009924402,"threshold_uncertainty_score":0.05248588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1936835263463012,"score_gpt":0.4732092990702447,"score_spread":0.2795257727239435,"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."}}