{"id":"W4412703854","doi":"10.1145/3696630.3728568","title":"Can Generative AI Produce Test Cases? An Experience from the Automotive Domain","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"European Commission","keywords":"Automotive industry; Generative grammar; Computer science; Test (biology); Domain (mathematical analysis); Artificial intelligence; Engineering; Mathematics; Aerospace engineering","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":[0.01232451,0.0006673129,0.0003571986,0.001038613,0.0007161594,0.001613981,0.002217198,0.001350514,0.002264876],"category_scores_gemma":[0.05623541,0.0003906454,0.0005249012,0.0008661853,0.00197892,0.002406304,0.001556679,0.001402253,0.000769869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001174193,"about_ca_system_score_gemma":0.0009102572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002811761,"about_ca_topic_score_gemma":0.003305082,"domain_scores_codex":[0.9857087,0.01061641,0.0005791121,0.0006228497,0.002070835,0.000402184],"domain_scores_gemma":[0.8883808,0.09760378,0.001516281,0.005905443,0.005632692,0.000960902],"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":[0.0009964699,0.002693764,0.04552092,0.001490356,0.0001456334,0.004085678,0.05653149,0.06419841,0.0467038,0.04024952,0.008034193,0.7293498],"study_design_scores_gemma":[0.0008517057,0.006366052,0.04474821,0.001290171,0.0004202113,0.01095033,0.03102073,0.4273053,0.1993316,0.06634631,0.2109686,0.0004008346],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7137377,0.001174734,0.2596636,0.002129753,0.00003595695,0.0003177997,0.0000971445,0.001759863,0.02108341],"genre_scores_gemma":[0.8680184,0.0004851192,0.1285715,0.0003859174,0.00001518717,0.00008592466,0.0002217429,0.0003564836,0.001859623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01232451,"threshold_uncertainty_score":0.06517905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01276337248502687,"score_gpt":0.3032364019357941,"score_spread":0.2904730294507673,"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."}}