{"id":"W4213397781","doi":"","title":"Mining Test Repositories for Automatic Detection of UI Performance Regressions in Android Apps","year":2016,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Android (operating system); Computer science; Test (biology); Mobile apps; World Wide Web; Operating system","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":[0.003389564,0.002152552,0.001763324,0.01102354,0.0004181161,0.001832659,0.002715426,0.001386623,0.000538398],"category_scores_gemma":[0.03376083,0.0008228371,0.001521335,0.004213959,0.0006745388,0.002569203,0.001404259,0.001049687,0.0007553106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007278218,"about_ca_system_score_gemma":0.00122835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005884172,"about_ca_topic_score_gemma":0.007769335,"domain_scores_codex":[0.9951645,0.0006750342,0.0006555407,0.001218015,0.002002921,0.0002840144],"domain_scores_gemma":[0.9648635,0.01674812,0.006718618,0.005373998,0.005502813,0.0007930329],"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":[0.0006499608,0.0009427647,0.3886059,0.001414012,0.0007647979,0.002260658,0.0008898468,0.1415771,0.02962495,0.001546897,0.01003458,0.4216885],"study_design_scores_gemma":[0.00004265447,0.0003150553,0.0466093,0.00009081578,0.0001587832,0.0007771558,0.0001916367,0.932343,0.01517001,0.001940795,0.002296853,0.00006392437],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7373841,0.002567145,0.2159552,0.0004074925,0.00009659176,0.0004106977,0.009047107,0.03270997,0.001421874],"genre_scores_gemma":[0.8714342,0.0004831614,0.1080628,0.00009469625,0.0000615391,0.0003702946,0.01766992,0.0008771409,0.0009463003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01102354,"threshold_uncertainty_score":0.01792598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008998518496103433,"score_gpt":0.2160289706201412,"score_spread":0.2070304521240378,"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."}}