{"id":"W7124996121","doi":"10.1109/aiware69974.2025.00012","title":"Turning Manual Tasks Into Actions: Assessing the Effectiveness of Gemini-Generated Selenium Tests","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":"University of Waterloo","funders":"","keywords":"Executable; HTML; Software; Test (biology); Hypertext; User interface","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003611313,0.0004384885,0.0005530207,0.0004120296,0.0009057421,0.0008095965,0.001354916,0.0002681825,0.00001397267],"category_scores_gemma":[0.003032488,0.0003191917,0.0001804543,0.002596887,0.0003445963,0.0006552209,0.0007173307,0.0005328123,0.000009031157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002799341,"about_ca_system_score_gemma":0.0009471201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001130617,"about_ca_topic_score_gemma":0.00001757404,"domain_scores_codex":[0.9959003,0.001655599,0.0007041616,0.0008416764,0.0003833228,0.0005148793],"domain_scores_gemma":[0.987211,0.01036904,0.0003433884,0.001293117,0.000699679,0.00008379277],"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":[0.0001434392,0.001077107,0.1209415,0.001850747,0.0006576745,0.00003332794,0.003477155,0.00371215,0.1468948,0.02197584,0.01293149,0.6863048],"study_design_scores_gemma":[0.0008177233,0.0005919681,0.1272637,0.004518967,0.0002169096,0.00006845921,0.0001503886,0.3610571,0.4544048,0.04886131,0.001173051,0.0008756618],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1395845,0.0008903181,0.8467509,0.0003870865,0.001601715,0.000564581,0.000002008426,0.005065961,0.005152896],"genre_scores_gemma":[0.9071586,0.00003602175,0.09195679,0.0001899647,0.00009654977,0.00007510267,0.000003520788,0.00002017579,0.00046329],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7675741,"threshold_uncertainty_score":0.999926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02708333145676899,"score_gpt":0.3548974381655703,"score_spread":0.3278141067088013,"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."}}