{"id":"W4285490476","doi":"10.1145/3533767.3543293","title":"ATUA: an update-driven app testing tool","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"European Commission","keywords":"Computer science; Oracle; Android (operating system); Random testing; Code coverage; Source code; Regression testing; Model-based testing; Code (set theory); Test case; Software engineering; Programming language; Machine learning; Software; Operating system; Software development; Regression analysis","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":[0.001405293,0.001625431,0.0007327952,0.002510766,0.0004192633,0.001244014,0.002840355,0.001236701,0.006736523],"category_scores_gemma":[0.01263314,0.0008531132,0.001171815,0.0007091921,0.0007230586,0.002307021,0.002195224,0.001277378,0.002925576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004360394,"about_ca_system_score_gemma":0.001155154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00287646,"about_ca_topic_score_gemma":0.002578537,"domain_scores_codex":[0.997976,0.0004501309,0.0001706755,0.0003049629,0.0009580051,0.0001401775],"domain_scores_gemma":[0.9932307,0.004199559,0.0004337289,0.001063686,0.0008971161,0.00017517],"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":[0.001277233,0.0005749608,0.01979517,0.002000162,0.0003637066,0.002988836,0.001681263,0.05485225,0.07038324,0.01527743,0.1104272,0.7203786],"study_design_scores_gemma":[0.0003320713,0.0009160799,0.008171038,0.0005641966,0.0003334155,0.004145644,0.0003840459,0.733303,0.1019069,0.02148736,0.1281035,0.0003528195],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04075909,0.001018767,0.5363345,0.0003795135,0.0001876853,0.0004831979,0.002858958,0.409954,0.008024239],"genre_scores_gemma":[0.5516866,0.0009010433,0.395807,0.0007964217,0.0001305088,0.001153781,0.009275357,0.02991549,0.01033384],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006736523,"threshold_uncertainty_score":0.02253592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03478549762453586,"score_gpt":0.2609590473911728,"score_spread":0.2261735497666369,"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."}}