{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04739402,0.001825404,0.001888955,0.002853832,0.0008100214,0.002945972,0.003880571,0.002912907,0.0050387],"category_scores_gemma":[0.122396,0.0006560507,0.00172791,0.002937304,0.001351019,0.003823632,0.003491067,0.00374162,0.001083693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003227128,"about_ca_system_score_gemma":0.003189471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004030284,"about_ca_topic_score_gemma":0.003291671,"domain_scores_codex":[0.9734677,0.01774227,0.001892143,0.00199798,0.004313699,0.0005862612],"domain_scores_gemma":[0.9263441,0.04824395,0.004149594,0.008869322,0.01140037,0.000992709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006490676,0.0003816916,0.01144496,0.0006335968,0.0007044091,0.0001330099,0.0001357251,0.720567,0.0009743529,0.04875837,0.009469406,0.2061485],"study_design_scores_gemma":[0.0000358583,0.0001768731,0.0005631549,0.00009792653,0.0000357353,0.00004530196,0.00002725056,0.9785756,0.001144717,0.01818537,0.001096662,0.00001540613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01686051,0.001121334,0.9756094,0.00104943,0.0001426492,0.000351455,0.001300635,0.001347195,0.002217402],"genre_scores_gemma":[0.4131552,0.0009893746,0.575073,0.0008479438,0.0002007826,0.00143227,0.005227135,0.0005078116,0.002566525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04739402,"threshold_uncertainty_score":0.2506465,"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."}}