{"id":"W4407948501","doi":"10.1109/access.2025.3545882","title":"Exploring the Integration of Generative AI Tools in Software Testing Education: A Case Study on ChatGPT and Copilot for Preparatory Testing Artifacts in Postgraduate Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Fanshawe College","funders":"","keywords":"Software testing; Computer science; Software; Software engineering; Artificial intelligence; Human–computer interaction; Engineering management; Engineering; Operating system","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":[0.0135419,0.0008346897,0.000621537,0.002025485,0.003656372,0.005288032,0.002744702,0.002427673,0.001704365],"category_scores_gemma":[0.02709373,0.0006429502,0.0006570747,0.00138956,0.005442498,0.003941642,0.005303215,0.00296679,0.0006375694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002931996,"about_ca_system_score_gemma":0.002389306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001690111,"about_ca_topic_score_gemma":0.005396328,"domain_scores_codex":[0.9854896,0.009857216,0.000425903,0.000830231,0.002156025,0.001241072],"domain_scores_gemma":[0.9694936,0.02156159,0.001995819,0.001801003,0.002406285,0.002741737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003436228,0.004398605,0.04197178,0.0006752354,0.00003919112,0.01474239,0.7806532,0.001688244,0.01861126,0.006478295,0.00222327,0.1281748],"study_design_scores_gemma":[0.0001527626,0.004721482,0.06174587,0.001127225,0.0001025711,0.009141491,0.8001879,0.01454401,0.02592978,0.005750513,0.07637008,0.0002263369],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897404,0.00008001321,0.006330813,0.0005217566,0.00001367581,0.0001527544,0.00001522829,0.00004068267,0.003104728],"genre_scores_gemma":[0.9844766,0.0001629669,0.01246746,0.0002705629,0.00001534778,0.0001458764,0.00004083891,0.0000693148,0.002350926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0135419,"threshold_uncertainty_score":0.07161725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6614717816677378,"score_gpt":0.5316937886462864,"score_spread":0.1297779930214514,"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."}}