{"id":"W1968593589","doi":"10.1080/10485252.2013.856431","title":"Goodness-of-fit tests based on the distance between the Dirichlet process and its base measure","year":2014,"lang":"en","type":"article","venue":"Journal of nonparametric statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet process; Mathematics; Concentration parameter; Hierarchical Dirichlet process; Latent Dirichlet allocation; Goodness of fit; Measure (data warehouse); Nonparametric statistics; Dirichlet distribution; Inference; Base (topology); Applied mathematics; Statistics; Bayesian probability; Mathematical analysis; Computer science; Topic model; Data mining; Artificial intelligence; Boundary value problem","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002943773,0.0001699758,0.0003617897,0.0002031119,0.0001471233,0.0001262376,0.001009995,0.00006176614,0.000004427386],"category_scores_gemma":[0.005460355,0.00008605701,0.00006249638,0.001260605,0.00009121748,0.0001401046,0.00005506124,0.0004260334,0.000001513805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002593859,"about_ca_system_score_gemma":0.0001503477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001730161,"about_ca_topic_score_gemma":7.545378e-7,"domain_scores_codex":[0.9977986,0.000477865,0.000516837,0.0001880608,0.0008016346,0.0002169668],"domain_scores_gemma":[0.9904662,0.007619381,0.0007606175,0.0004199137,0.0005996017,0.0001342429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009410246,0.0003553455,0.0126158,0.0002786003,0.0001406362,0.00005050014,0.0007948228,0.00149049,0.00007621444,0.3152802,0.005870413,0.6629528],"study_design_scores_gemma":[0.001475139,0.001473762,0.05960437,0.0003961979,0.000255701,0.00006036357,0.00003228772,0.7500765,0.001396014,0.1827546,0.001977906,0.0004971526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004626265,0.0003783847,0.9927004,0.001574046,0.0001963944,0.0001491628,0.00004678887,0.000007322338,0.0003212287],"genre_scores_gemma":[0.7376444,0.00001926501,0.2618479,0.0003548215,0.0001053554,0.00000233572,3.241296e-7,0.000009102825,0.0000165909],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.748586,"threshold_uncertainty_score":0.653695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04767650177503057,"score_gpt":0.3154568157603176,"score_spread":0.267780313985287,"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."}}