{"id":"W7161988216","doi":"10.82308/24563","title":"Two advancements in statistical learning methods","year":2025,"lang":"en","type":"dissertation","venue":"","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Missing data; Deep learning; Regression; Kernel (algebra); Feature (linguistics); Regularization (linguistics); Kernel method; Trait","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02936152,0.002805339,0.003059916,0.004464233,0.001102456,0.006431703,0.004105279,0.004110236,0.004453104],"category_scores_gemma":[0.09781589,0.001533667,0.00522154,0.005598706,0.005551544,0.008536312,0.007091501,0.0165204,0.003739042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002881171,"about_ca_system_score_gemma":0.004839754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00295108,"about_ca_topic_score_gemma":0.001942056,"domain_scores_codex":[0.9719046,0.01369332,0.002100073,0.004623624,0.006984801,0.0006934342],"domain_scores_gemma":[0.8915638,0.08460025,0.002021353,0.01127151,0.009214314,0.001328764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001613569,0.0001118291,0.003013663,0.001156169,0.0006212576,0.0001229124,0.0004223848,0.02282826,0.000697408,0.5280398,0.02170455,0.4211203],"study_design_scores_gemma":[0.00009310494,0.0001809735,0.001511416,0.0007168252,0.0001744488,0.0002892905,0.0001258136,0.1781376,0.001234146,0.6859587,0.1314379,0.0001397867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001274181,0.01683845,0.9635964,0.01225028,0.001640264,0.00004961308,0.0003499361,0.0004115064,0.003589396],"genre_scores_gemma":[0.08163573,0.04229783,0.8417343,0.00825317,0.01311101,0.0006415348,0.001520266,0.001155317,0.009650824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02936152,"threshold_uncertainty_score":0.1552804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01631505100635292,"score_gpt":0.421469065197761,"score_spread":0.405154014191408,"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."}}