{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003799346,0.00009933606,0.00009759807,0.00008714432,0.0004210183,0.000134805,0.001128576,0.00001927283,0.00006384647],"category_scores_gemma":[0.0002312105,0.00009683696,0.00002803299,0.0005440563,0.00001739648,0.0003067779,0.0009582668,0.0001792497,0.00003007397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000477933,"about_ca_system_score_gemma":0.00006532162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001225589,"about_ca_topic_score_gemma":0.000001917334,"domain_scores_codex":[0.9988862,0.0000806809,0.0001499312,0.0003675317,0.0002735012,0.0002421482],"domain_scores_gemma":[0.9989414,0.0002194314,0.00005534477,0.0006716695,0.00005258793,0.00005955523],"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":[0.00000699368,0.0003806177,0.06418493,0.00001697545,0.00001875824,0.000193045,0.001021837,0.002977772,0.001015712,0.08901521,0.2377059,0.6034623],"study_design_scores_gemma":[0.000229446,0.000543524,0.004520173,0.00001182858,0.000005530891,0.0002668587,0.00001976238,0.8819035,0.0005700554,0.09378748,0.01756283,0.0005790133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03356313,0.00002649902,0.9073536,0.0006318121,0.0002933417,0.0001684477,0.000002573356,0.05184007,0.006120484],"genre_scores_gemma":[0.4433103,1.826209e-7,0.555486,0.0009555866,0.00003071725,0.00003720214,0.000002699942,0.000007863426,0.0001694243],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8789257,"threshold_uncertainty_score":0.3948897,"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."}}