{"id":"W4308627374","doi":"10.1145/3558489.3559073","title":"On the effectiveness of data balancing techniques in the context of ML-based test case prioritization","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Regression testing; Computer science; Context (archaeology); Prioritization; Regression analysis; Regression; Machine learning; Test data; Risk-based testing; Data mining; Reliability engineering; Artificial intelligence; Software; Software system; Statistics; Engineering; Software 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":[0.02384683,0.001926706,0.00112624,0.006239089,0.0009782908,0.002967022,0.002054109,0.001516746,0.001076956],"category_scores_gemma":[0.1224433,0.0003575505,0.001098107,0.003697605,0.001126362,0.004754649,0.001687514,0.002178228,0.0007627266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000919111,"about_ca_system_score_gemma":0.001729477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002049648,"about_ca_topic_score_gemma":0.002312161,"domain_scores_codex":[0.9754951,0.01189484,0.002443225,0.003819293,0.005700685,0.0006469354],"domain_scores_gemma":[0.8466312,0.1219387,0.008908974,0.01379761,0.007425529,0.001298009],"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":[0.001980725,0.001628229,0.1114853,0.001558732,0.0009050537,0.0001914453,0.0007089273,0.07993153,0.01986367,0.002826675,0.006490363,0.7724293],"study_design_scores_gemma":[0.0004437495,0.004121051,0.1039106,0.000848962,0.000944414,0.000972589,0.001940488,0.8073924,0.05061587,0.01232517,0.01630349,0.0001811785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7286304,0.01888174,0.2310316,0.00264106,0.0006190373,0.0009508284,0.002848767,0.006968753,0.007427735],"genre_scores_gemma":[0.8760419,0.00118295,0.1180369,0.0003134577,0.0002750811,0.0002539062,0.003128143,0.0002273975,0.0005401588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02384683,"threshold_uncertainty_score":0.1261156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03438440068923974,"score_gpt":0.2944197283149523,"score_spread":0.2600353276257125,"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."}}