{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002053011,0.0005129582,0.0007202896,0.001264201,0.0006524578,0.001138675,0.0007926052,0.0002400411,0.00001342144],"category_scores_gemma":[0.001313059,0.0005242302,0.0001191657,0.004143074,0.0001415514,0.001186215,0.0005363124,0.0003542218,0.000006926023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001172408,"about_ca_system_score_gemma":0.0009993588,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03749168,"about_ca_topic_score_gemma":0.002507113,"domain_scores_codex":[0.9948606,0.0005437264,0.00177717,0.001626669,0.0004631957,0.000728672],"domain_scores_gemma":[0.99615,0.0004602093,0.0005328224,0.002129666,0.000495149,0.0002321275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"case_report","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002646029,0.004785539,0.2507269,0.002236883,0.0002226379,0.4885504,0.03956237,0.02915708,0.02094558,0.02545436,0.05109919,0.0869945],"study_design_scores_gemma":[0.0007247051,0.00007889407,0.0005616832,0.001011025,0.00003692994,0.01006538,0.0001249553,0.9838125,0.002855412,0.0001601362,0.00005209461,0.0005163208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4117094,0.00008823133,0.5464778,0.0001663546,0.001145226,0.00100049,0.000003699056,0.0374807,0.001928051],"genre_scores_gemma":[0.7959353,0.000004589571,0.2028246,0.0003353296,0.00009371209,0.000119685,0.000008411627,0.00002400643,0.0006543675],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9546554,"threshold_uncertainty_score":0.9998983,"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."}}