{"id":"W4407771189","doi":"10.1145/3641554.3701917","title":"Quantitative Evaluation of Using Large Language Models and Retrieval-Augmented Generation in Computer Science Education","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Language model; Information retrieval","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":[0.001741102,0.00005136831,0.00007693278,0.0003305066,0.00006168581,0.00006275855,0.0001714352,0.00002325692,0.000002596153],"category_scores_gemma":[0.00006371889,0.0000497984,0.000009060222,0.0007303251,0.00003238508,0.0007699633,0.0001287518,0.00003747171,2.715754e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269015,"about_ca_system_score_gemma":0.0007276928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001327336,"about_ca_topic_score_gemma":0.00005799852,"domain_scores_codex":[0.9990236,0.00008680546,0.0001915221,0.0002664095,0.0003278446,0.0001037762],"domain_scores_gemma":[0.9993407,0.00002311763,0.00005793994,0.0002217708,0.0003387223,0.00001777732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006081599,0.0001287599,0.0006518954,0.00002585172,0.000005829135,1.981181e-7,0.004908025,0.2384926,0.08520014,0.591997,0.00001590687,0.07856777],"study_design_scores_gemma":[0.0002540265,0.00001074722,0.0005518901,0.00003381582,0.000004834002,4.520348e-7,0.0001423463,0.9836239,0.0101868,0.005146519,4.991385e-7,0.00004420566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.477049,0.000128986,0.5223206,0.00005770449,0.0001051427,0.0001175294,2.119818e-7,0.000007760316,0.000213089],"genre_scores_gemma":[0.7755793,0.00000256836,0.2243011,0.00008938282,0.000009441782,0.000001657309,0.000001420571,0.00000108435,0.00001406374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7451313,"threshold_uncertainty_score":0.203072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09692513595673274,"score_gpt":0.3935415129644818,"score_spread":0.2966163770077491,"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."}}