{"id":"W4387790211","doi":"10.2139/ssrn.4602038","title":"Parsimonious Bayesian Model-Based Clustering with Dissimilarities","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Cluster analysis; Bayesian probability; Computer science; Artificial intelligence; Econometrics; Data mining; 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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001970081,0.0005940371,0.0005698451,0.000566253,0.0005473869,0.0008958422,0.003486906,0.0003045007,0.000002635146],"category_scores_gemma":[0.00007149052,0.0005258038,0.0002379933,0.0004625442,0.0001435947,0.0004547293,0.002132432,0.008623779,0.00001320533],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002784204,"about_ca_system_score_gemma":0.01028639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007907904,"about_ca_topic_score_gemma":0.001161061,"domain_scores_codex":[0.9921095,0.0001869102,0.0005407127,0.001027534,0.001266099,0.004869271],"domain_scores_gemma":[0.9975731,0.0001413458,0.0003638956,0.001331418,0.0002798623,0.0003103828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005490868,0.00004597559,0.00006862401,0.0001013188,0.000184715,0.0001425579,0.0002329491,0.9635465,0.0000113293,0.005798982,0.00003726657,0.02977488],"study_design_scores_gemma":[0.0004836973,0.0002494438,0.0000207789,0.0002672229,0.00001829399,0.0002583615,0.0001619714,0.762141,0.00004893261,0.2358281,0.00003979325,0.0004823287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009112043,0.0007145553,0.9937561,0.003040757,0.0004707643,0.0003449352,0.00001454179,0.000589312,0.0001578303],"genre_scores_gemma":[0.768192,0.00269851,0.2228821,0.0001842008,0.0006224154,0.0001664407,0.00002789806,0.000299439,0.004926975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.770874,"threshold_uncertainty_score":0.9997194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02578557196786586,"score_gpt":0.2935396233393311,"score_spread":0.2677540513714652,"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."}}