{"id":"W4410944754","doi":"10.21203/rs.3.rs-6795375/v1","title":"Introduction of a Method to Choose the Number of Clusters of a Mixed Dataset under Kproto","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Computer science; Chemistry; Statistics; Mathematics","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.006982376,0.0002626176,0.0006536917,0.0008002912,0.0001252875,0.00008732996,0.004276535,0.000226852,0.0000654997],"category_scores_gemma":[0.001473673,0.0002066207,0.0001769547,0.002406719,0.0003623736,0.0001949563,0.01318891,0.001555251,0.00002123857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000298472,"about_ca_system_score_gemma":0.0009770255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001280933,"about_ca_topic_score_gemma":0.00003929865,"domain_scores_codex":[0.9926028,0.002372776,0.0007808942,0.001073338,0.002484733,0.0006855166],"domain_scores_gemma":[0.9923361,0.001460696,0.0002864301,0.003853266,0.001885036,0.0001784951],"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":[0.001520321,0.001733747,0.0004976484,0.02510531,0.001216543,0.00004053967,0.008411434,0.2354977,0.01135318,0.04011877,0.1215657,0.5529391],"study_design_scores_gemma":[0.004453763,0.001984841,0.01359863,0.008199877,0.0001309315,0.0001025557,0.006267733,0.4480976,0.3034551,0.1142708,0.09717132,0.002266946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003001786,0.0001297338,0.9835107,0.007664873,0.0002899584,0.003339371,0.001782338,0.00003862557,0.0002426692],"genre_scores_gemma":[0.05022025,0.0001853198,0.9432293,0.00008454475,0.0005949236,0.002011104,0.000714062,0.00006913827,0.002891404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5506722,"threshold_uncertainty_score":0.9947922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0772401653793962,"score_gpt":0.4882824658172666,"score_spread":0.4110423004378704,"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."}}