{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008492214,0.0001449171,0.0002237092,0.0001219654,0.00007084371,0.0001109345,0.001170175,0.00005395766,0.000006297268],"category_scores_gemma":[0.0003389445,0.0001598471,0.00004235672,0.0004281615,0.00001208975,0.0006758677,0.001896217,0.0001530196,0.000003381598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009833826,"about_ca_system_score_gemma":0.0001669776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000245312,"about_ca_topic_score_gemma":0.00001088063,"domain_scores_codex":[0.998595,0.00007410645,0.0002960792,0.0005384723,0.0001716829,0.0003246769],"domain_scores_gemma":[0.9980086,0.0002698503,0.00005363822,0.001379616,0.0001923075,0.00009599596],"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":[0.000001316895,0.00006005117,0.000006575892,0.0003177724,0.00005050607,0.00001050634,0.0002592179,0.009881406,0.1520986,0.002983101,0.0003277593,0.8340032],"study_design_scores_gemma":[0.0002312273,0.00002428617,0.0001066075,0.00004872809,0.000005781525,0.0000173652,0.00001308042,0.9521344,0.03618176,0.00004009995,0.01104416,0.0001525444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001948376,0.0006144024,0.9977608,0.00009415736,0.0007885281,0.000162281,0.00006508901,0.0001112067,0.0002086581],"genre_scores_gemma":[0.005080575,0.00002676522,0.9942734,0.000006798176,0.0001888279,0.00004268903,0.0002298969,0.00002518653,0.0001258148],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9422529,"threshold_uncertainty_score":0.6518375,"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."}}