{"id":"W2778728785","doi":"10.5430/air.v7n1p15","title":"Estimating the number of clusters using diversity","year":2017,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Outlier; Silhouette; Computer science; Pattern recognition (psychology); Entropy (arrow of time); Single-linkage clustering; Cluster (spacecraft); Ground truth; Artificial intelligence; Statistic; Mathematics; Data mining; Fuzzy clustering; Statistics; CURE data clustering algorithm; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006803065,0.0013757,0.002440946,0.00727645,0.002626745,0.003362668,0.002693533,0.002630351,0.0008944196],"category_scores_gemma":[0.03386156,0.0008780399,0.001476564,0.004132612,0.002270846,0.004209595,0.004197785,0.002173058,0.0007740223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001955168,"about_ca_system_score_gemma":0.001779812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004010482,"about_ca_topic_score_gemma":0.005037246,"domain_scores_codex":[0.9933484,0.001798947,0.0004785802,0.002141089,0.001867023,0.0003658032],"domain_scores_gemma":[0.9785373,0.01290202,0.002299236,0.002348391,0.00329504,0.00061804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008462392,0.0001887624,0.04351984,0.0005925383,0.0008096377,0.0004250587,0.001740457,0.4774753,0.0127698,0.04286085,0.01174832,0.4070233],"study_design_scores_gemma":[0.00006073234,0.00008985945,0.00559087,0.0001224777,0.00007779424,0.0003623516,0.0004365485,0.9042374,0.005376069,0.07912745,0.004394055,0.0001243493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04885091,0.001199155,0.946241,0.0004219296,0.00005654639,0.0001103034,0.0003740153,0.0006102608,0.002135908],"genre_scores_gemma":[0.5717149,0.0006481977,0.4236878,0.0002672323,0.0002384164,0.0002735952,0.001559216,0.0002827335,0.001327894],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00727645,"threshold_uncertainty_score":0.0359785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3684176429372282,"score_gpt":0.505386192201522,"score_spread":0.1369685492642938,"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."}}