{"id":"W4407771524","doi":"10.1145/3641554.3701809","title":"How Effective and Efficient are Student-Written Software Tests?","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Universitas Brawijaya","keywords":"Computer science; Software testing; Software; Software engineering; Programming language","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":[0.0002346556,0.000148285,0.0001712858,0.0001547424,0.0001589189,0.0004468276,0.0005285685,0.00005843669,7.732261e-7],"category_scores_gemma":[0.0006996894,0.0001205554,0.00003874687,0.0004321234,0.00005553771,0.0001163227,0.0005915081,0.0001216958,0.00000417884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004305739,"about_ca_system_score_gemma":0.00002543283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002641182,"about_ca_topic_score_gemma":0.000004725613,"domain_scores_codex":[0.9989966,0.00005557557,0.00009770881,0.0004426513,0.0001844932,0.0002230385],"domain_scores_gemma":[0.9985136,0.0007675462,0.00005074854,0.0004976042,0.0001097793,0.0000606637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000008565275,0.0004184378,0.4417184,0.000148336,0.0000817558,0.0000990952,0.0008608407,0.00005443757,0.0001150091,0.02380313,0.06120243,0.4714895],"study_design_scores_gemma":[0.0008979611,0.0003843422,0.9166379,0.0006104381,0.00003533487,0.00004575056,0.0001014329,0.02056444,0.002137333,0.05523972,0.002635931,0.0007094413],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05332464,0.0002789469,0.9295676,0.002282808,0.000241413,0.0003622481,0.000001240195,0.01309597,0.0008450903],"genre_scores_gemma":[0.8240743,0.000003029601,0.1742175,0.0007215432,0.00001856865,0.00006392392,3.3899e-7,0.000006049422,0.000894709],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7707497,"threshold_uncertainty_score":0.4916105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008202861097243937,"score_gpt":0.2658796855053294,"score_spread":0.2576768244080854,"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."}}