{"id":"W4386708429","doi":"10.32920/24133128","title":"Evaluation methodology for deep learning imputation models","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Toronto Metropolitan University; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Computer science; Mean squared error; Deep learning; Artificial intelligence; Missing data; Machine learning; Regression; Data mining; Artificial neural network; Pattern recognition (psychology); Statistics; Mathematics","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":[0.007522088,0.000193185,0.0002662286,0.0003307501,0.0001138088,0.0002113299,0.001157262,0.0003382448,0.000008614352],"category_scores_gemma":[0.00150913,0.0001995872,0.0001065548,0.0002271017,0.00002385693,0.0004503112,0.001055818,0.0003703058,0.00003668878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002362649,"about_ca_system_score_gemma":0.0002564843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004781903,"about_ca_topic_score_gemma":0.00001838276,"domain_scores_codex":[0.9970646,0.0008350227,0.0004266113,0.0008879651,0.0005371604,0.0002486275],"domain_scores_gemma":[0.9968338,0.0008385134,0.0003908589,0.0008928868,0.001001079,0.00004288079],"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":[0.00000345458,0.0000135564,0.000004836676,0.00006014555,0.00004074206,2.749192e-7,0.0005376677,0.2192081,0.0004966766,0.2277665,0.001367888,0.5505002],"study_design_scores_gemma":[0.00007305433,0.0000202335,0.0000627175,0.00000980051,0.00001910707,6.937115e-7,0.0000151754,0.5472367,0.001408282,0.4508645,0.0001738038,0.0001158825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004324561,0.00006427897,0.9934976,0.001172132,0.0007331156,0.001362823,0.000009502528,0.002273031,0.0008443483],"genre_scores_gemma":[0.02826067,0.00006087217,0.968467,0.0001133979,0.00008362018,0.001895065,0.0005964893,0.00002983644,0.0004930381],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5503843,"threshold_uncertainty_score":0.8138931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4106801675677966,"score_gpt":0.4456876198808968,"score_spread":0.03500745231310021,"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."}}