{"id":"W7026617208","doi":"","title":"Accounting for variance and hyperparameter optimization in machine learning benchmarks","year":2022,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Compute Canada; Canadian Institute for Advanced Research","keywords":"Test (biology); Decision tree","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006408126,0.0003688349,0.0003623097,0.0004231536,0.007142526,0.0002505014,0.0005417002,0.0002986469,0.00009553338],"category_scores_gemma":[0.0003576827,0.0004724436,0.0001331287,0.0005349322,0.0001063991,0.000988139,0.0003354476,0.0008302931,0.000004252104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002410073,"about_ca_system_score_gemma":0.0008330056,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0317794,"about_ca_topic_score_gemma":0.003878889,"domain_scores_codex":[0.9974022,0.0003230263,0.000460624,0.0009317394,0.0004610793,0.0004213158],"domain_scores_gemma":[0.998339,0.0003937405,0.000574288,0.0003501388,0.0001926666,0.0001501643],"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":[0.0006089865,0.0002353862,0.07524635,0.0004171344,0.0001274606,0.0003019987,0.03929918,0.7796968,0.00193205,0.06738724,0.00009667195,0.03465075],"study_design_scores_gemma":[0.0009615732,0.0001264372,0.03431343,0.0001492519,0.00009450763,0.0002538504,0.004909083,0.9036139,0.0001048582,0.0001453369,0.0548677,0.0004601068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4322292,0.07381179,0.4491432,0.004097394,0.005360833,0.002745237,0.0003055748,0.0004220096,0.03188484],"genre_scores_gemma":[0.8761537,0.001936462,0.07137461,0.0002080811,0.000219898,0.0002111323,0.007691497,0.00006639838,0.04213821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4439246,"threshold_uncertainty_score":0.9997727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00776089845587945,"score_gpt":0.1938290518964026,"score_spread":0.1860681534405232,"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."}}