{"id":"W4397026406","doi":"10.1109/access.2024.3402543","title":"Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Software Engineering Research","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Huawei Technologies (Canada); University of Alberta","funders":"University of Alberta","keywords":"Overfitting; Computer science; Artificial intelligence; Deep learning; Machine learning; Artificial neural network","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":[0.0007531053,0.0001587637,0.0001727376,0.0005894286,0.00005265461,0.0005156016,0.001470277,0.00007057133,0.000005064278],"category_scores_gemma":[0.0003037238,0.0001742119,0.00005916267,0.001134669,0.00001983688,0.001145208,0.0002911616,0.0005404477,0.000037329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006227036,"about_ca_system_score_gemma":0.0001944064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001594649,"about_ca_topic_score_gemma":0.000006771049,"domain_scores_codex":[0.998098,0.00007024522,0.0002255976,0.0006408394,0.0004453778,0.0005199347],"domain_scores_gemma":[0.9988745,0.0004922565,0.00002407245,0.0004102872,0.00005240391,0.0001464806],"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":[0.00000271355,0.00002324366,0.0009534151,0.0001835678,0.000008530885,0.00006198481,0.001593538,0.9790307,0.0007449633,0.001196294,0.0002818794,0.01591918],"study_design_scores_gemma":[0.0001244212,0.00001757565,0.0008349963,0.0001801638,0.000001678816,0.00000409501,0.000008182406,0.9960191,0.001059404,0.000279774,0.001261434,0.0002091488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07865402,0.000768981,0.9173914,0.0001307034,0.0007181792,0.0001956152,2.937307e-7,0.0007431793,0.001397656],"genre_scores_gemma":[0.9744538,0.000003084701,0.02497799,0.0001839543,0.0001020597,0.0001031067,0.000001128177,0.00003494395,0.0001399553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8957998,"threshold_uncertainty_score":0.7104155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06739076771566944,"score_gpt":0.2979730627291863,"score_spread":0.2305822950135168,"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."}}