{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005042892,0.001117305,0.001462891,0.002467227,0.001325776,0.002947998,0.002736187,0.00225809,0.006105852],"category_scores_gemma":[0.01774232,0.0006539844,0.001420519,0.001959424,0.001471984,0.002685679,0.003988524,0.003241209,0.003747955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069871,"about_ca_system_score_gemma":0.001833068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001803442,"about_ca_topic_score_gemma":0.003426722,"domain_scores_codex":[0.9961466,0.001186812,0.0003215048,0.001111248,0.001012324,0.0002216214],"domain_scores_gemma":[0.9927393,0.002627287,0.0004701162,0.001540832,0.002248118,0.0003744058],"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":[0.0007597648,0.0003489341,0.005291599,0.00082341,0.0002796701,0.0002760686,0.0004759495,0.02734758,0.02912592,0.1089891,0.02154363,0.8047383],"study_design_scores_gemma":[0.0001818429,0.000270863,0.003573377,0.0001782394,0.0001212232,0.000774132,0.0002460179,0.8153689,0.0196953,0.1025851,0.05680563,0.0001993519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001337219,0.0001389224,0.9965797,0.0002162162,0.0001893865,0.0001024092,0.0001397233,0.000775575,0.0005208774],"genre_scores_gemma":[0.01987021,0.0001305256,0.9765322,0.0002101683,0.0003078718,0.0003654538,0.0003889078,0.0004229525,0.001771634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006105852,"threshold_uncertainty_score":0.02666968,"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."}}