{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008362151,0.0001986909,0.0002624696,0.0002986195,0.0004326278,0.00005062777,0.0004202733,0.00007643141,0.000005814848],"category_scores_gemma":[0.001879957,0.0002145802,0.00003999153,0.0004819905,0.0000453842,0.0001244006,0.0001106877,0.0004797727,0.000001913093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005429253,"about_ca_system_score_gemma":0.00002799241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004707457,"about_ca_topic_score_gemma":6.966669e-7,"domain_scores_codex":[0.9985816,0.0003159702,0.0001808081,0.0004806545,0.0001351971,0.0003057002],"domain_scores_gemma":[0.9937447,0.005548012,0.00005342846,0.0005027465,0.00004240261,0.000108745],"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":[0.00001630102,0.00006181917,0.001283349,0.00005880654,0.00005839098,0.00004247413,0.0005147803,0.0722447,0.0004788056,0.0005569091,0.0003310099,0.9243526],"study_design_scores_gemma":[0.001121692,0.001214124,0.008178595,0.00009766944,0.00008809091,0.002621386,0.00003709484,0.9631484,0.002003675,0.008555774,0.01187808,0.001055467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007288221,0.0002053356,0.9714318,0.0001748072,0.0003760256,0.0003398768,0.00001107915,0.02016863,0.000004215806],"genre_scores_gemma":[0.1322387,0.00001778917,0.8669199,0.0002262486,0.00001477075,0.0005412533,0.000002128078,0.00002387528,0.00001532478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9232972,"threshold_uncertainty_score":0.8750327,"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."}}