{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003081501,0.00006248467,0.00008015669,0.00005586716,0.00006671457,0.0001662784,0.0007061877,0.00003236089,0.0000236657],"category_scores_gemma":[0.00002499212,0.00005713116,0.00002289528,0.00066807,0.00001535677,0.0008199131,0.0004436808,0.000178122,0.00003422129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003244211,"about_ca_system_score_gemma":0.0000209423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009769441,"about_ca_topic_score_gemma":0.00005935187,"domain_scores_codex":[0.9991682,0.0000296277,0.0001917143,0.0003859199,0.00009733081,0.0001272778],"domain_scores_gemma":[0.9991969,0.00007898272,0.00002532241,0.0006589061,0.00001731739,0.00002250829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001253969,0.00003315521,0.0001206116,0.00002620639,0.00001025426,0.000007972169,0.0007032265,0.007383302,0.0008534616,0.6483384,0.0004616917,0.3420605],"study_design_scores_gemma":[0.00003968671,0.0000150496,0.000144312,0.00001229215,0.000001877109,0.000003281068,0.0001127488,0.9164872,0.000973652,0.007045032,0.07505426,0.0001105867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005425673,0.0002730045,0.9851646,0.00106408,0.00004546712,0.00007026802,8.771702e-7,0.000725081,0.01211407],"genre_scores_gemma":[0.4535517,0.0001049199,0.545303,0.0001510324,0.00001717394,0.00001217283,0.000005858565,0.000004916435,0.0008491571],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9091039,"threshold_uncertainty_score":0.2329741,"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."}}