{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001079046,0.0003032467,0.0003389636,0.0006840042,0.000187647,0.0001822479,0.001689454,0.00008566244,0.00008300369],"category_scores_gemma":[0.0009598819,0.0003409381,0.0001351893,0.002485667,0.00003181368,0.0003616085,0.00094849,0.001206052,0.00002738634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000582932,"about_ca_system_score_gemma":0.0001788181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002634558,"about_ca_topic_score_gemma":6.449285e-7,"domain_scores_codex":[0.9967114,0.0001080381,0.0003841111,0.0007862397,0.001037609,0.0009725881],"domain_scores_gemma":[0.9973378,0.001554175,0.00003200327,0.0007674932,0.00005367381,0.0002548171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006231563,0.0001802719,0.07722432,0.0000653056,0.00001192684,0.0001012881,0.0005168917,0.9166539,0.00009805784,0.00009489917,0.0003238703,0.004723028],"study_design_scores_gemma":[0.0009229572,0.0002252261,0.07186915,0.00004533051,0.000003935281,0.00005871221,0.00006238608,0.8994974,0.0008401312,0.00004776432,0.02562281,0.000804181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1963644,0.0007116129,0.8006675,0.0001300617,0.0002566873,0.0003825579,0.000007784425,0.001460718,0.00001865393],"genre_scores_gemma":[0.8643171,0.000003616537,0.1346862,0.0001383117,0.00007199349,0.0006631489,0.00002187728,0.00006569698,0.0000320527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6679527,"threshold_uncertainty_score":0.9999043,"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."}}