{"id":"W4401373758","doi":"10.1214/24-aoas1877","title":"Probabilistic contrastive dimension reduction for case-control study data","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Canadian Institute for Advanced Research; National Cancer Institute; National Science Foundation; National Institutes of Health; National Institute of Environmental Health Sciences; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Dimensionality reduction; Dimension (graph theory); Reduction (mathematics); Probabilistic logic; Computer science; Statistics; Data reduction; Artificial intelligence; Natural language processing; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004749844,0.0000977247,0.0001132686,0.00002537348,0.00008625281,0.00002635171,0.0001815156,0.00004429366,0.000007841327],"category_scores_gemma":[0.00009952002,0.00006927795,0.00002201161,0.00006896704,0.00007434025,0.000002877755,0.00006112267,0.00005496619,0.000002397803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000403731,"about_ca_system_score_gemma":0.0000720512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005658106,"about_ca_topic_score_gemma":0.00000907161,"domain_scores_codex":[0.9991999,0.00004173016,0.0002131308,0.0003188233,0.0001057359,0.0001206274],"domain_scores_gemma":[0.9991201,0.00008913199,0.00007988784,0.0005367504,0.0001421342,0.00003196763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002329604,0.0004770856,0.00001031435,0.0002623922,0.0006118977,0.00001914549,0.001206231,0.001550747,0.6604241,0.0316538,0.1607811,0.1406736],"study_design_scores_gemma":[0.01000546,0.008310993,0.004756493,0.000266823,0.002890694,0.0004947893,0.0236182,0.1609548,0.5147943,0.1051017,0.1665483,0.00225735],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.230203,0.001533162,0.7522666,0.001080269,0.0008453505,0.004724707,0.008618321,0.00005396456,0.000674581],"genre_scores_gemma":[0.9980373,0.00005252431,0.001093435,0.00007208587,0.0001819907,0.0001256611,0.0003085835,0.00001705467,0.0001113882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7678343,"threshold_uncertainty_score":0.2825073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08856121255749513,"score_gpt":0.3719493295497239,"score_spread":0.2833881169922288,"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."}}