{"id":"W2964055823","doi":"10.1093/biomet/asx023","title":"Data integration with high dimensionality","year":2017,"lang":"en","type":"article","venue":"Biometrika","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Directorate for Mathematical and Physical Sciences","keywords":"Mathematics; Bayesian information criterion; Consistency (knowledge bases); Curse of dimensionality; Model selection; Sample size determination; Infinity; Bayesian probability; Feature selection; Selection (genetic algorithm); Statistics; Data mining; Machine learning; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02587076,0.001429893,0.003262341,0.001931012,0.001613511,0.00354094,0.003552092,0.00315387,0.002379098],"category_scores_gemma":[0.1096864,0.001598566,0.002725878,0.004357563,0.002652419,0.005592637,0.008355048,0.005604501,0.0009135742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260799,"about_ca_system_score_gemma":0.001990244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00289048,"about_ca_topic_score_gemma":0.002528509,"domain_scores_codex":[0.9849554,0.009155519,0.001043247,0.002097955,0.002453284,0.0002945515],"domain_scores_gemma":[0.9266573,0.05366677,0.003312408,0.01155002,0.004026019,0.0007874115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000827494,0.0004975024,0.01737362,0.001297443,0.001262488,0.001799324,0.00217828,0.3805896,0.009717217,0.2982789,0.00740827,0.27877],"study_design_scores_gemma":[0.00005028786,0.00007587311,0.001346826,0.00006115326,0.00006739714,0.000252975,0.0001187879,0.7776669,0.001959288,0.2137579,0.004590072,0.00005250773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007350256,0.0003000785,0.9910076,0.0004910465,0.00004859168,0.00007534967,0.000121878,0.0002111189,0.000393918],"genre_scores_gemma":[0.1174069,0.000406302,0.8784893,0.0006170333,0.0001810747,0.0007294581,0.0007831382,0.0001459025,0.001240968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02587076,"threshold_uncertainty_score":0.1368192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3822180638818842,"score_gpt":0.4671006075363553,"score_spread":0.08488254365447112,"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."}}