{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006083699,0.00007854915,0.0001444885,0.00007989255,0.0001862627,0.0001103841,0.0005163761,0.00004062742,0.0002053058],"category_scores_gemma":[0.007930961,0.00004913865,0.00001067361,0.0001486816,0.0001219227,0.0001417629,0.0002256314,0.00006787812,0.00003163643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001407627,"about_ca_system_score_gemma":0.00002637753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001413968,"about_ca_topic_score_gemma":0.00002961504,"domain_scores_codex":[0.9992641,0.00004319057,0.0001366792,0.0002233614,0.0002208215,0.0001118578],"domain_scores_gemma":[0.9976044,0.0006907725,0.0001379962,0.001416688,0.0000920602,0.000058048],"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":[0.00003970769,0.0001207797,0.001868256,0.00002887052,0.00003179996,0.000008322753,0.00001655733,1.258756e-8,0.001380096,0.8309466,0.00660921,0.1589499],"study_design_scores_gemma":[0.0007261298,0.0002507337,0.2056762,0.0001186501,0.00007616945,0.000007950979,0.00002973785,0.0009223769,0.006637076,0.7759668,0.009273408,0.0003146864],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1909909,0.00003880034,0.8001643,0.0009589326,0.0003853494,0.000227601,0.0007650512,0.00007538252,0.006393646],"genre_scores_gemma":[0.4966123,0.000003562312,0.5030697,0.00002941727,0.00005006076,0.000002571962,0.00002857542,0.000005965363,0.0001977934],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3056214,"threshold_uncertainty_score":0.9494674,"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."}}