{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005327443,0.002493553,0.00210695,0.002117478,0.001079036,0.001943692,0.003825566,0.002360205,0.00211449],"category_scores_gemma":[0.02291325,0.00123772,0.001500609,0.001066279,0.001307577,0.003921404,0.002847696,0.004872996,0.0009874946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001474422,"about_ca_system_score_gemma":0.002438606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01016139,"about_ca_topic_score_gemma":0.01398124,"domain_scores_codex":[0.9973128,0.0004910664,0.0002582952,0.000732803,0.0009043323,0.0003005523],"domain_scores_gemma":[0.9887146,0.004960357,0.00170319,0.002022512,0.002118859,0.0004805102],"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":[0.0005109867,0.0006416229,0.02613948,0.000248673,0.0004046409,0.0005785601,0.0005144181,0.4700038,0.011259,0.003486252,0.008618567,0.477594],"study_design_scores_gemma":[0.00001277043,0.0001432157,0.001282123,0.00004356434,0.00006270801,0.00009068304,0.00003125255,0.9901797,0.004274554,0.002794859,0.001057833,0.00002679267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1179618,0.001787325,0.8661626,0.001494194,0.0002262499,0.0001807041,0.0003197107,0.009049728,0.00281769],"genre_scores_gemma":[0.8598173,0.0005060358,0.1319235,0.001135399,0.000174228,0.000188476,0.0009626838,0.0007185059,0.004573892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01016139,"threshold_uncertainty_score":0.02817458,"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."}}