{"id":"W4388717896","doi":"10.48550/arxiv.2311.07762","title":"Finite Mixtures of Multivariate Poisson-Log Normal Factor Analyzers for Clustering Count Data","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Mixture model; Multivariate statistics; Context (archaeology); Poisson distribution; Computer science; Count data; Covariance matrix; Model selection; Factor analysis; Multivariate normal distribution; Gaussian; Mathematics; Data mining; Statistics; Algorithm; Artificial intelligence; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008906795,0.001766271,0.001683812,0.00299297,0.00145708,0.003026471,0.005674784,0.002840462,0.005306229],"category_scores_gemma":[0.02975123,0.001455443,0.003412116,0.003496095,0.002506898,0.002994437,0.003369359,0.00527515,0.00319934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002199593,"about_ca_system_score_gemma":0.002664679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00541689,"about_ca_topic_score_gemma":0.006580379,"domain_scores_codex":[0.9940712,0.003412339,0.0002740183,0.001004502,0.0009774193,0.0002605406],"domain_scores_gemma":[0.9912943,0.005761971,0.0006483763,0.001364413,0.0006820232,0.0002489695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001867292,0.0000973958,0.003216854,0.0002917587,0.0001760669,0.000198742,0.0005255117,0.2351093,0.006378355,0.6490009,0.007556285,0.09726202],"study_design_scores_gemma":[0.00001620672,0.00002756138,0.000495818,0.00005440515,0.0000353049,0.0001476819,0.00004240647,0.7805162,0.001446745,0.2092604,0.007891322,0.00006601381],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001106282,0.0001295035,0.9980122,0.00007256476,0.00002444157,0.000034896,0.0001110517,0.0002341548,0.0002749006],"genre_scores_gemma":[0.05484351,0.0006304568,0.9378085,0.000206564,0.0001344533,0.0008808525,0.001314727,0.0006052766,0.003575745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008906795,"threshold_uncertainty_score":0.04710418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1921081809697489,"score_gpt":0.2653047640172036,"score_spread":0.07319658304745474,"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."}}