{"id":"W4417036956","doi":"10.5753/sbqs.2025.15010","title":"Automated Test Case Generation in a Real-World System Using a Customized AI Agent: An Experience Report","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":"Optech (Canada)","funders":"","keywords":"Context (archaeology); Component (thermodynamics); Process (computing); Quality (philosophy); Test (biology); Test case; Software; Keyword-driven testing; Test Management Approach","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005719208,0.0008290799,0.0004297237,0.0006339985,0.0004254932,0.001042535,0.001848741,0.001024786,0.001897758],"category_scores_gemma":[0.01299704,0.0004208949,0.0004237743,0.0004826808,0.0009135677,0.001007694,0.0009938788,0.0009032179,0.0007174456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006592011,"about_ca_system_score_gemma":0.0007111813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00208374,"about_ca_topic_score_gemma":0.002675001,"domain_scores_codex":[0.9966645,0.00204055,0.0001967673,0.0003124854,0.0006093141,0.0001764211],"domain_scores_gemma":[0.9864325,0.009734238,0.0003875165,0.001647161,0.00132963,0.0004690614],"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":[0.001827521,0.009677382,0.02712998,0.001058686,0.0002446754,0.005066262,0.01940171,0.1147709,0.1612656,0.005640739,0.007991759,0.6459247],"study_design_scores_gemma":[0.001119261,0.01368514,0.03315077,0.0002907647,0.0003215502,0.005812696,0.005001568,0.5331912,0.3371629,0.002734879,0.06718323,0.0003460372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8310441,0.0002037706,0.1570795,0.0003227874,0.00003393448,0.0008158205,0.0001958541,0.002410394,0.007893619],"genre_scores_gemma":[0.7505355,0.0002276429,0.2445967,0.00009590379,0.00001482805,0.0002556175,0.0005915941,0.0003074998,0.003374702],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005719208,"threshold_uncertainty_score":0.03024644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06728239215720491,"score_gpt":0.3727870787301468,"score_spread":0.3055046865729419,"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."}}