{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004266874,0.00005873208,0.00012464,0.00004200073,0.00008740363,0.00006050323,0.0005211158,0.00002478785,0.000198356],"category_scores_gemma":[0.00008647767,0.00004103359,0.00003403552,0.0001306333,0.00007866458,0.0001110852,0.000007258458,0.0001461414,0.000007479269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012931,"about_ca_system_score_gemma":0.0005896848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007854907,"about_ca_topic_score_gemma":0.0006802859,"domain_scores_codex":[0.9992975,0.00007443649,0.0002796644,0.00005773209,0.000127794,0.0001628536],"domain_scores_gemma":[0.9991592,0.0001396606,0.0001551063,0.0001747864,0.0001355378,0.0002357708],"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":[0.000002296043,0.000004957738,0.0004482499,0.00001397379,0.00002465161,0.0001465761,0.001899905,0.001162404,0.000005765542,0.133256,0.01396492,0.8490703],"study_design_scores_gemma":[0.0006977001,0.0001591532,0.005304284,0.0002234156,0.00007421098,0.002103501,0.00006621882,0.4305762,0.0001116895,0.54,0.02032536,0.0003583523],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002592858,0.00006651093,0.993228,0.0005631827,0.000317164,0.00002592249,0.0000233783,0.000001687029,0.003181319],"genre_scores_gemma":[0.1156956,0.000004386557,0.8836773,0.0003350122,0.00006959558,1.858312e-7,2.518827e-7,0.000004344545,0.0002133853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8487119,"threshold_uncertainty_score":0.2171859,"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."}}