{"id":"W4417132523","doi":"10.1109/saner-c66551.2025.00015","title":"Assessing Data Augmentation-Induced Bias in Training and Testing of Machine Learning Models","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Debugging; Training set; Software; Test data; Test (biology); Training (meteorology); Non-regression testing; Keyword-driven testing; Software testing","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04082102,0.00158523,0.00127804,0.001427151,0.00099545,0.002040296,0.001854854,0.002555319,0.001069262],"category_scores_gemma":[0.2231389,0.0007571227,0.001152268,0.001271247,0.003009951,0.002986789,0.003613195,0.003451975,0.0005093538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001216545,"about_ca_system_score_gemma":0.00190595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002855301,"about_ca_topic_score_gemma":0.003515509,"domain_scores_codex":[0.9754882,0.0155671,0.001565972,0.002631059,0.004133535,0.0006141717],"domain_scores_gemma":[0.7182247,0.2283629,0.009900182,0.02834487,0.01388572,0.001281617],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003721588,0.0009021249,0.1578556,0.001040541,0.001102821,0.0004715093,0.001244494,0.6177276,0.01436218,0.01210503,0.008026217,0.1814402],"study_design_scores_gemma":[0.0002679693,0.001163367,0.02119,0.0003524809,0.0002197528,0.0003967333,0.0003065402,0.921308,0.027463,0.02291215,0.004329377,0.00009070882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6908574,0.00275036,0.2958893,0.001763146,0.0004235237,0.0004992119,0.001688761,0.002602805,0.003525513],"genre_scores_gemma":[0.9005082,0.0002315193,0.0944933,0.0006116882,0.00009706894,0.0003431898,0.002764782,0.0003229608,0.0006273964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.959179,"threshold_uncertainty_score":0.2158847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4312538849540782,"score_gpt":0.4003276714823415,"score_spread":0.03092621347173669,"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."}}