{"id":"W7125939950","doi":"10.1109/ase63991.2025.00251","title":"Who’s to Blame? Rethinking the Brittleness of Automated Web GUI Testing from a Pragmatic Perspective","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; University of Waterloo","funders":"","keywords":"Automation; Perspective (graphical); Web application; Test (biology); Test case; Software testing; Brittleness","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002148468,0.0004751731,0.0007307596,0.0004351419,0.000635014,0.0007054094,0.002902698,0.0002314349,0.0000285959],"category_scores_gemma":[0.01891858,0.0003739773,0.0001688924,0.004189929,0.0003053251,0.0003146401,0.001991444,0.0005598736,0.00002441309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003362356,"about_ca_system_score_gemma":0.001248226,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01098515,"about_ca_topic_score_gemma":0.0001793802,"domain_scores_codex":[0.995854,0.0006057169,0.001034286,0.001138259,0.0007177261,0.000649976],"domain_scores_gemma":[0.9867021,0.008894408,0.0005004499,0.00208814,0.001683435,0.0001314517],"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":[0.000140243,0.001350515,0.04821903,0.001213791,0.001409781,0.0001885247,0.1577444,0.004270178,0.009955906,0.2081681,0.2389755,0.3283641],"study_design_scores_gemma":[0.0002518174,0.000159921,0.006689239,0.004730875,0.00008907924,0.00001296298,0.0003823457,0.7634416,0.002203457,0.2215784,0.0000918762,0.0003683926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07113356,0.001408073,0.8400175,0.0152961,0.001352267,0.002279537,0.00003444399,0.04314121,0.02533729],"genre_scores_gemma":[0.6436002,0.000006474222,0.3543354,0.001495434,0.00006361335,0.00007283493,8.999384e-7,0.00002218806,0.000402962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7591714,"threshold_uncertainty_score":0.9998712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0263521555170315,"score_gpt":0.3083849450295481,"score_spread":0.2820327895125165,"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."}}