{"id":"W2950118368","doi":"10.48550/arxiv.1206.4658","title":"Dirichlet Process with Mixed Random Measures: A Nonparametric Topic\\n Model for Labeled Data","year":2012,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Dirichlet process; Nonparametric statistics; Random forest; Computer science; Measure (data warehouse); Mixture model; Pattern recognition (psychology); Dirichlet distribution; Artificial intelligence; Process (computing); Hierarchical Dirichlet process; Segmentation; Latent Dirichlet allocation; Mathematics; Data mining; Topic model; Statistics","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0030258,0.001248659,0.001722117,0.0007586228,0.0006603872,0.0004609553,0.008745777,0.000900434,0.0000214013],"category_scores_gemma":[0.0004091411,0.001183252,0.0004399888,0.002813522,0.0003689138,0.00210381,0.003699085,0.00127365,0.00002764788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000282602,"about_ca_system_score_gemma":0.001558719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000835785,"about_ca_topic_score_gemma":0.0001280226,"domain_scores_codex":[0.9922203,0.0007225355,0.0007486517,0.004204708,0.0004608739,0.001642953],"domain_scores_gemma":[0.9897721,0.0009090503,0.001022646,0.006225552,0.001205337,0.0008653588],"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":[0.007124353,0.003064516,0.002031025,0.003214979,0.002990573,0.0003318763,0.005693053,0.5686647,0.00009942891,0.2990009,0.001575992,0.1062086],"study_design_scores_gemma":[0.00694417,0.0001581521,0.00004914786,0.0002838742,0.001142597,0.00001857037,0.00005159093,0.9305815,0.0001375495,0.05841781,0.0007454656,0.001469644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01521935,0.000864608,0.9782836,0.0001966999,0.0009107535,0.003017726,0.0003012017,0.0002108187,0.0009952071],"genre_scores_gemma":[0.7505368,0.0005673622,0.2451815,0.0001711,0.0002571326,0.00002002724,0.000103965,0.00007949858,0.003082662],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7353174,"threshold_uncertainty_score":0.9990618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2036947857767872,"score_gpt":0.2498801374655578,"score_spread":0.04618535168877061,"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."}}