{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.003796671,0.0001124437,0.0001635078,0.0001216136,0.004180655,0.0005990598,0.005204703,0.00006361121,0.00003783841],"category_scores_gemma":[0.00182559,0.00008785894,0.0000746964,0.000454946,0.001242031,0.0008570385,0.008622949,0.0005913157,0.0001628954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128129,"about_ca_system_score_gemma":0.000153965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00254641,"about_ca_topic_score_gemma":0.00007375716,"domain_scores_codex":[0.9968508,0.0003088901,0.000313962,0.0004373925,0.001374121,0.0007147758],"domain_scores_gemma":[0.9965597,0.000642062,0.0001308901,0.001860689,0.0006779163,0.0001287611],"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":[0.00005034647,0.0001496455,0.004081922,0.00007107908,0.00004570901,0.00007737782,0.005085547,0.04997858,0.004567447,0.07877783,0.00003816965,0.8570763],"study_design_scores_gemma":[0.00001612507,0.00002844872,0.0003699315,0.00004365202,0.000001599559,0.00001380259,0.0003642162,0.9120841,0.01862352,0.06834649,0.00001620541,0.00009191192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2052693,0.0000134622,0.7920024,0.001069195,0.0003126125,0.0002134977,0.000001459819,0.00003020865,0.001087767],"genre_scores_gemma":[0.8881286,0.000005958137,0.1116151,0.00001122704,0.0001252948,0.000006402076,1.693606e-7,0.000008900783,0.00009838668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8621055,"threshold_uncertainty_score":0.9993951,"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."}}