{"id":"W4401163968","doi":"10.1109/bmsb62888.2024.10608270","title":"Optimizing Data Quality in Deep Learning through Advanced Analytics","year":2024,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Quality (philosophy); Analytics; Data science; Data analysis; Data quality; Learning analytics; Artificial intelligence; Machine learning; Data mining; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01950057,0.001255752,0.00126035,0.001848238,0.0006650498,0.004105312,0.002078032,0.001448348,0.0008719068],"category_scores_gemma":[0.06860223,0.0005465965,0.0007372817,0.002167922,0.002269208,0.007450643,0.004407643,0.003538654,0.0002340827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002685655,"about_ca_system_score_gemma":0.002808298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003070377,"about_ca_topic_score_gemma":0.002811805,"domain_scores_codex":[0.9904696,0.003757034,0.0008037686,0.001162021,0.003331794,0.0004757882],"domain_scores_gemma":[0.9591938,0.02441351,0.003452955,0.005484252,0.006764983,0.0006905298],"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":[0.0007996245,0.000354484,0.02188483,0.000652097,0.0003037665,0.0001644467,0.000443175,0.6005123,0.009466981,0.05151911,0.00527645,0.3086228],"study_design_scores_gemma":[0.00003432103,0.0001590719,0.001391312,0.00009693758,0.00003579259,0.0000579039,0.00009070353,0.9288897,0.01003926,0.05739501,0.001780991,0.00002901672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04688821,0.001048491,0.9476659,0.002118531,0.00007992713,0.00009925656,0.0002729429,0.0009411221,0.0008856814],"genre_scores_gemma":[0.7093102,0.0008169822,0.2869692,0.0007495605,0.0001104861,0.000148877,0.000752345,0.000275586,0.0008668262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01950057,"threshold_uncertainty_score":0.1031301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07458423191664845,"score_gpt":0.3779632087282159,"score_spread":0.3033789768115674,"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."}}