{"id":"W4416455941","doi":"10.7717/peerj-cs.3309","title":"The Silhouette coefficient and the Davies-Bouldin index are more informative than Dunn index, Calinski-Harabasz index, Shannon entropy, and Gap statistic for unsupervised clustering internal evaluation of two convex clusters","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Silhouette; Cluster analysis; Rand index; Pattern recognition (psychology); Ground truth; Consensus clustering; Euclidean distance; Correlation clustering","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005510658,0.000321251,0.0004314577,0.0004220268,0.001093618,0.00108187,0.002359494,0.00006137125,0.000001260569],"category_scores_gemma":[0.0005196544,0.0002122211,0.00007342413,0.001228431,0.002483773,0.001005859,0.003192935,0.0004039452,9.752703e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002783602,"about_ca_system_score_gemma":0.0004863967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001693457,"about_ca_topic_score_gemma":0.0001205099,"domain_scores_codex":[0.9955573,0.0003475819,0.0006857439,0.0007849578,0.001896881,0.0007275491],"domain_scores_gemma":[0.9957978,0.001482012,0.0004086071,0.000841974,0.001295061,0.0001745732],"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":[0.0006152953,0.0001070965,0.007529434,0.0003988074,0.0001626694,0.000008967187,0.02046039,0.402385,0.00030904,0.01136353,0.0001522117,0.5565076],"study_design_scores_gemma":[0.004060003,0.0001164844,0.02687488,0.0002289656,0.00002153014,0.0000245505,0.0005193836,0.964752,0.0003373733,0.002775573,0.00007492906,0.0002143312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0819464,0.0002704879,0.9131182,0.0023276,0.0007179963,0.001498084,0.00002549475,0.00005384738,0.00004187218],"genre_scores_gemma":[0.9855249,0.00003389925,0.01374683,0.0004146438,0.00005406095,0.0001538978,0.000002783655,0.00001168501,0.00005731246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9035785,"threshold_uncertainty_score":0.9999551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0262903710357365,"score_gpt":0.3489306135391119,"score_spread":0.3226402425033754,"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."}}