{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006001971,0.000822669,0.0004860142,0.0007374086,0.0002637423,0.001176303,0.0006553465,0.0006312188,0.001699086],"category_scores_gemma":[0.04919115,0.0002230858,0.0002215991,0.0003996135,0.0003050228,0.001108522,0.0007798991,0.0006245,0.0005243476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004579801,"about_ca_system_score_gemma":0.0008916602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008402915,"about_ca_topic_score_gemma":0.0007953827,"domain_scores_codex":[0.9960052,0.002235941,0.0004380045,0.0004830006,0.0006554775,0.0001823503],"domain_scores_gemma":[0.9576489,0.0333358,0.002490608,0.001726697,0.003361785,0.00143611],"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":[0.01199412,0.01285342,0.07624478,0.0009318219,0.0002036606,0.0001734348,0.004879586,0.03309463,0.08283316,0.00126062,0.001279538,0.7742512],"study_design_scores_gemma":[0.002581651,0.08964874,0.2009218,0.0003176617,0.0007250037,0.0006097584,0.004651878,0.392396,0.2956509,0.003444538,0.008642179,0.0004099788],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863754,0.00005955696,0.01184461,0.00003391907,0.00002197729,0.0002247834,0.00005424078,0.0004355837,0.0009498166],"genre_scores_gemma":[0.9798091,0.00006675933,0.01904168,0.00002825789,0.00001003612,0.0002448209,0.0001137661,0.00003295535,0.0006526014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006001971,"threshold_uncertainty_score":0.0317418,"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."}}