{"id":"W2109904733","doi":"10.2307/3315985","title":"Estimating the number of clusters","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Estimator; Nonparametric statistics; Computation; Mathematics; Constant (computer programming); Random variate; Cluster (spacecraft); Set (abstract data type); Function (biology); Population; Data set; Algorithm; Applied mathematics; Probability density function; Statistics; Computer science; Combinatorics; Random variable","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":[0.005160661,0.0007468396,0.001415348,0.003462644,0.001722817,0.002874493,0.002483995,0.001827536,0.002562328],"category_scores_gemma":[0.03921577,0.0007498593,0.0008231857,0.002608596,0.002041916,0.003175489,0.002613702,0.00179988,0.0006833382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002356176,"about_ca_system_score_gemma":0.001656361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01394115,"about_ca_topic_score_gemma":0.008756147,"domain_scores_codex":[0.9957901,0.001570821,0.0001944064,0.001396989,0.0007894061,0.0002582892],"domain_scores_gemma":[0.9847392,0.009474605,0.0009777463,0.001875363,0.002457649,0.0004753864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001085046,0.0001282044,0.05760435,0.0004986443,0.0006591942,0.0001979401,0.001219583,0.2816631,0.005002005,0.2598893,0.01404193,0.3780108],"study_design_scores_gemma":[0.00007320958,0.00008182079,0.01130434,0.0001588944,0.0001230517,0.0001726715,0.0003091342,0.7888451,0.003956506,0.1841645,0.01069646,0.0001143624],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07552855,0.001563511,0.9177806,0.0005890885,0.0001003044,0.0002452007,0.0006209732,0.0003057154,0.003266085],"genre_scores_gemma":[0.4811704,0.0006340583,0.5134304,0.0001576572,0.0001208298,0.0003068964,0.001104345,0.00009689452,0.002978557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01394115,"threshold_uncertainty_score":0.02771997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01626948947403848,"score_gpt":0.2627838807639077,"score_spread":0.2465143912898692,"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."}}