{"id":"W4413199870","doi":"10.3102/ip.25.2197254","title":"Evaluating the Efficacy of Generative AI in Automating Assessment in Introductory Computer Science Courses (Poster 47)","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Data Processing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Generative grammar; Software engineering; Artificial intelligence; Human–computer interaction","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":[0.001066883,0.0001029677,0.0001525066,0.0002484515,0.00005570806,0.00004822376,0.0003255173,0.00002641298,0.000006844725],"category_scores_gemma":[0.0001630571,0.00007721056,0.00001261991,0.0006983436,0.0001621436,0.0003501016,0.000178827,0.0002396981,7.075097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002138526,"about_ca_system_score_gemma":0.0001716673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001422613,"about_ca_topic_score_gemma":0.00002573078,"domain_scores_codex":[0.99902,0.0000500285,0.0003237785,0.0002099923,0.0002072756,0.0001889126],"domain_scores_gemma":[0.9993591,0.0002248203,0.00004092099,0.0002837617,0.0000794587,0.00001192261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008633523,0.00009715923,0.006422281,0.000168404,0.00001614067,0.000002170597,0.001594913,0.4800248,0.2361711,0.004384193,0.0007875118,0.2703227],"study_design_scores_gemma":[0.0002386139,0.00002999666,0.02427419,0.000231051,0.000002736056,6.243241e-7,0.00006084556,0.9079679,0.06636613,0.0007112693,0.00002684602,0.00008984553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5719512,0.0001054441,0.4256282,0.0004055208,0.0001981558,0.0003020206,0.000001547877,0.0002549678,0.001152986],"genre_scores_gemma":[0.7317143,0.000003619153,0.2680665,0.000153575,0.00002383137,0.00002041522,0.000001799953,0.000006577814,0.00000939474],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4279431,"threshold_uncertainty_score":0.3148555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02715858326500707,"score_gpt":0.4017002551157903,"score_spread":0.3745416718507832,"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."}}