{"id":"W4225714444","doi":"10.1007/s10664-022-10125-6","title":"Tracking bad updates in mobile apps: a search-based approach","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Thompson Rivers University; Queen's University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Android (operating system); Computer science; Benchmark (surveying); Genetic programming; Machine learning; Sorting; Mobile apps; Artificial intelligence; World Wide Web","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":[0.0041549,0.001497435,0.002945299,0.01795242,0.001364293,0.004374091,0.003295245,0.004001861,0.003160713],"category_scores_gemma":[0.03512613,0.0007482301,0.001458856,0.01067193,0.0009336322,0.00671621,0.002521536,0.001685519,0.001873077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057937,"about_ca_system_score_gemma":0.001712015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01246888,"about_ca_topic_score_gemma":0.02214521,"domain_scores_codex":[0.9928349,0.001312037,0.0007043661,0.001507483,0.003162069,0.0004790984],"domain_scores_gemma":[0.963302,0.02402013,0.004061481,0.002619397,0.005206555,0.0007904511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002237183,0.002518436,0.3584864,0.002061183,0.001286603,0.001455903,0.001835603,0.02935093,0.01151071,0.01036513,0.02077764,0.5581142],"study_design_scores_gemma":[0.0001764883,0.001661669,0.1471882,0.0004227784,0.001461708,0.003649278,0.002941186,0.7924342,0.01262361,0.02668721,0.01045599,0.0002977666],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7395105,0.01318737,0.2057552,0.003197799,0.0004655441,0.001448154,0.01146852,0.004915243,0.02005182],"genre_scores_gemma":[0.9396834,0.001179958,0.04982265,0.0003754895,0.0002303563,0.0001701269,0.003492004,0.000130563,0.004915465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01795242,"threshold_uncertainty_score":0.02479261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0278380218906817,"score_gpt":0.2811678476185983,"score_spread":0.2533298257279166,"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."}}