{"id":"W7160855074","doi":"10.69987/jacs.2025.50902","title":"Performance Evaluation of Prompt Generation Strategies for AI Agents in Online Programming Education","year":2025,"lang":"","type":"article","venue":"Journal of Advanced Computing Systems","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Python (programming language); Hybrid learning; Online learning; Tracking (education); Empirical research; Cognition","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"],"consensus_categories":[],"category_scores_codex":[0.00751802,0.0002874009,0.000674532,0.000848889,0.000290604,0.0005315334,0.0006799193,0.0001466909,4.650647e-7],"category_scores_gemma":[0.0005443046,0.0002877566,0.0001799316,0.001006653,0.00004973204,0.001265209,0.00008977905,0.0006496821,2.891657e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006608115,"about_ca_system_score_gemma":0.003460258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005655306,"about_ca_topic_score_gemma":0.00001463884,"domain_scores_codex":[0.9951221,0.0008430735,0.002227898,0.0004217078,0.0009539836,0.0004312348],"domain_scores_gemma":[0.9936463,0.000191815,0.002850972,0.0003523795,0.002884852,0.00007364639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002754644,0.0003411138,0.001609991,0.0005619384,0.00004073214,3.728063e-7,0.002561511,0.4708235,0.000416739,0.0005611708,0.00003038502,0.523025],"study_design_scores_gemma":[0.001804904,0.0007683542,0.006353089,0.007454489,0.0001187686,0.00003343962,0.002989696,0.9762076,0.0001462206,0.00007232806,0.003832301,0.0002188148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6032577,0.003351767,0.3872139,0.0002492271,0.004810821,0.001076175,7.990507e-7,0.00001968223,0.0000198723],"genre_scores_gemma":[0.9075289,0.00002874428,0.09167308,0.00003214162,0.0006208381,0.00002425383,0.000008797229,0.00001663943,0.00006657217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5228062,"threshold_uncertainty_score":0.9999574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05967443082002329,"score_gpt":0.388593024381778,"score_spread":0.3289185935617547,"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."}}