{"id":"W4410344404","doi":"10.1145/3735553","title":"Large Language Models for Automated Web-Form-Test Generation: An Empirical Study","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test (biology); Software engineering; Web application; Natural language processing; Programming language; World Wide Web; Information retrieval","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":[0.001031804,0.0001928966,0.0002743344,0.0003199258,0.0002336288,0.00007263767,0.0004315382,0.0001446648,0.000001996026],"category_scores_gemma":[0.001588337,0.0001878038,0.00005967462,0.0003762717,0.00001753275,0.000227046,0.00002788231,0.0002111484,8.398846e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003436586,"about_ca_system_score_gemma":0.00006556336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001812392,"about_ca_topic_score_gemma":0.00001271353,"domain_scores_codex":[0.9987487,0.0001633281,0.0002358732,0.0004673255,0.00009266054,0.0002920949],"domain_scores_gemma":[0.9960326,0.003052853,0.00003277102,0.0007172469,0.00008163228,0.00008291172],"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":[0.0001625725,0.005317067,0.009873119,0.0005689695,0.0007884064,0.0001150582,0.03610881,0.2947405,0.004995228,0.006808804,0.009807663,0.6307138],"study_design_scores_gemma":[0.0006277429,0.0005282648,0.0006150365,0.00002382858,0.00003959587,0.00002562179,0.00005928701,0.9940003,0.000804028,0.002780361,0.0002818047,0.0002141893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03186381,0.0001023441,0.9517866,0.0001846738,0.0004041658,0.0003196405,0.00001929288,0.01531672,0.000002701135],"genre_scores_gemma":[0.3135576,0.000006053249,0.6859276,0.0002336763,0.00002706647,0.0001727869,0.000005927025,0.00001375696,0.00005550555],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6992598,"threshold_uncertainty_score":0.7658416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1082660934781946,"score_gpt":0.3902024629079375,"score_spread":0.281936369429743,"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."}}