{"id":"W2069169007","doi":"10.1109/wse.2012.6320526","title":"Visual testing of Graphical User Interfaces: An exploratory study towards systematic definitions and approaches","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphical user interface; Computer science; Graphical user interface testing; Human–computer interaction; User interface; Visualization; User interface design; User experience design; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001115089,0.0001280828,0.0002521258,0.0001509781,0.00009227692,0.00008799516,0.0003334945,0.00004280209,9.501285e-7],"category_scores_gemma":[0.0006289579,0.00009745264,0.00002225908,0.0003848732,0.00006683467,0.0006786746,0.0002756928,0.00009609408,0.000002097754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009972296,"about_ca_system_score_gemma":0.00003029435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004106555,"about_ca_topic_score_gemma":0.00000546065,"domain_scores_codex":[0.9988186,0.0002400862,0.0003108271,0.0002242077,0.0002057716,0.0002005128],"domain_scores_gemma":[0.9987873,0.0005256124,0.00010472,0.0003880198,0.00007884497,0.0001154374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001009117,0.006564292,0.858505,0.006484959,0.0001791282,0.00001168175,0.05858422,0.00001273642,0.0003648291,0.056063,0.0005518432,0.01266823],"study_design_scores_gemma":[0.003659156,0.01651483,0.3847062,0.01557437,0.0009044004,0.00103973,0.04844786,0.3726644,0.01957867,0.1314534,0.00001227754,0.005444674],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7430254,0.0001235575,0.2528411,0.00001376105,0.0000538611,0.0003097733,4.756179e-7,0.003337079,0.0002950151],"genre_scores_gemma":[0.8066491,5.722494e-7,0.1932282,0.00002550066,0.00001484426,0.00007119106,3.35866e-7,0.000007464254,0.000002818353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4737988,"threshold_uncertainty_score":0.3974003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2284178662324735,"score_gpt":0.3159080840569035,"score_spread":0.08749021782443,"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."}}