{"id":"W4205529760","doi":"10.1145/3502297","title":"Automated, Cost-effective, and Update-driven App Testing","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Centre National de la Recherche Scientifique; European Commission","keywords":"Computer science; Dependability; Oracle; Code coverage; Random testing; Android (operating system); Model-based testing; Test case; Cyclomatic complexity; Automation; Source code; Code (set theory); Test suite; Random oracle; Set (abstract data type); Software engineering; Distributed computing; Programming language; Machine learning; Software; Operating system; Encryption","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":[0.002919322,0.001771063,0.0009345435,0.002903284,0.000532944,0.001659205,0.003255212,0.001547512,0.001845198],"category_scores_gemma":[0.02524596,0.0007453322,0.001269516,0.00113107,0.001217128,0.003472946,0.002508893,0.001316734,0.0007290658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004815,"about_ca_system_score_gemma":0.002604668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003349077,"about_ca_topic_score_gemma":0.005227069,"domain_scores_codex":[0.9910915,0.003318446,0.0004346372,0.0008976819,0.003828514,0.0004290886],"domain_scores_gemma":[0.9700027,0.01731408,0.002336286,0.007434828,0.002484967,0.0004272808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006953966,0.0009925532,0.0249818,0.0008876346,0.0002882557,0.0007789396,0.000841223,0.2197662,0.06923053,0.01154387,0.00488253,0.6651111],"study_design_scores_gemma":[0.0001222857,0.0008416562,0.006297393,0.0001379173,0.0002141048,0.000967185,0.0002516984,0.9197266,0.04899441,0.01738507,0.004977495,0.00008426043],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1570542,0.001466599,0.8192918,0.0007029131,0.00006126994,0.0006426671,0.000426583,0.01552427,0.004829803],"genre_scores_gemma":[0.7675431,0.000333252,0.2292902,0.0002002978,0.00003506151,0.0003196809,0.0006312526,0.0005701125,0.001076983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003349077,"threshold_uncertainty_score":0.01543903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07249387697246641,"score_gpt":0.3145700562029212,"score_spread":0.2420761792304548,"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."}}