{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004134102,0.00006753257,0.0001107061,0.00008857495,0.0001107224,0.00002285808,0.001292542,0.00001657225,0.000003976017],"category_scores_gemma":[0.001496636,0.00004030597,0.00001909804,0.0005540218,0.00004341996,0.00009780352,0.0003752776,0.0001343669,1.675715e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000310563,"about_ca_system_score_gemma":0.00006550191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007300157,"about_ca_topic_score_gemma":0.00001927834,"domain_scores_codex":[0.9986474,0.000647861,0.000174734,0.0002042967,0.0002392971,0.00008641832],"domain_scores_gemma":[0.9880004,0.01074995,0.00009899766,0.001088003,0.0000549513,0.000007732207],"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":[0.0002301139,0.003783807,0.2039635,0.000943312,0.00004695306,0.001209107,0.006678756,0.0006865239,0.01320452,0.4336544,0.03270008,0.3028989],"study_design_scores_gemma":[0.001331023,0.003108583,0.02467929,0.001326291,0.00003306995,0.001065928,0.0007931507,0.5683755,0.2958411,0.1023101,0.0004045906,0.0007313602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09552133,0.00004525589,0.8997168,0.000640274,0.00005652866,0.001006845,0.00003998223,0.002069453,0.0009035221],"genre_scores_gemma":[0.9778539,4.20251e-7,0.02167882,0.0003789946,0.000003952268,0.00007138435,0.000006611897,0.00000449594,0.000001411904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8823326,"threshold_uncertainty_score":0.2401886,"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."}}