{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007072553,0.0003839819,0.0005839108,0.0003685507,0.0001432037,0.0001173972,0.004268074,0.0003656158,0.00001028778],"category_scores_gemma":[0.0001800615,0.0004096318,0.000263374,0.0005072427,0.00009662389,0.0005132725,0.005687754,0.0004576657,0.000008626628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009375838,"about_ca_system_score_gemma":0.0002466858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005420526,"about_ca_topic_score_gemma":0.0001659138,"domain_scores_codex":[0.9973081,0.0001884547,0.0003570356,0.001533079,0.0001353628,0.0004779963],"domain_scores_gemma":[0.995917,0.0005825426,0.0004698241,0.002634312,0.0002197519,0.0001765615],"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":[0.00045159,0.0003785124,0.001645258,0.002004248,0.001701453,0.0005515806,0.002681897,0.7349029,0.002196147,0.232213,0.002851235,0.01842221],"study_design_scores_gemma":[0.0005519749,0.00004553506,0.0005737257,0.0001277915,0.0001018472,0.000001336854,0.00001266271,0.9686036,0.0003596303,0.02864266,0.0005467633,0.0004325454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005059505,0.00005152489,0.9920024,0.0001307465,0.001143072,0.0004783654,0.0007425612,0.0002058035,0.0001860321],"genre_scores_gemma":[0.7622558,0.0001226687,0.235968,0.00007707843,0.0001179387,0.000002015437,0.0001634163,0.00003848085,0.001254544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7571963,"threshold_uncertainty_score":0.9998356,"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."}}