{"id":"W4416943890","doi":"10.1007/s00357-025-09522-5","title":"Implications of Different Encodings of Binned Data when Clustering","year":2025,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Encoding (memory); Latent class model; ENCODE; Class (philosophy); Pattern recognition (psychology); Medoid; Latent variable; Single-linkage clustering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0468373,0.000700401,0.001060595,0.0027062,0.00153912,0.006173578,0.002609991,0.00181358,0.001956994],"category_scores_gemma":[0.3072625,0.0006612247,0.00095086,0.004906362,0.003199191,0.009074188,0.003593809,0.00365905,0.0003693579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003790318,"about_ca_system_score_gemma":0.001761419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003975252,"about_ca_topic_score_gemma":0.004769667,"domain_scores_codex":[0.9418401,0.04676848,0.003443109,0.002501334,0.004578121,0.0008688928],"domain_scores_gemma":[0.7209245,0.228057,0.008426394,0.02159434,0.01937121,0.001626447],"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":[0.005402608,0.0006525126,0.04831062,0.001534538,0.0007605346,0.0004737673,0.007725656,0.3251565,0.009348635,0.2298053,0.01022957,0.3605998],"study_design_scores_gemma":[0.0003109917,0.0004860875,0.01235922,0.0010159,0.0001914484,0.0004728214,0.006077524,0.6816877,0.01401326,0.2779355,0.005171475,0.0002779531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4136867,0.001983887,0.5692377,0.006264571,0.0005119417,0.000510605,0.001703331,0.001146528,0.004954823],"genre_scores_gemma":[0.7061318,0.0002937288,0.2914038,0.0005784028,0.0000441314,0.0001994063,0.0007452311,0.0001846967,0.0004187622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0468373,"threshold_uncertainty_score":0.2477023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.088042672940701,"score_gpt":0.3476281171019941,"score_spread":0.2595854441612931,"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."}}