{"id":"W4407681763","doi":"10.1145/3641554.3701844","title":"Integrating Small Language Models with Retrieval-Augmented Generation in Computing Education: Key Takeaways, Setup, and Practical Insights","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Toronto","funders":"Universitas Brawijaya","keywords":"Key (lock); Computer science; Multimedia; Data science; Information retrieval; Operating system","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":[0.000251338,0.0001161516,0.0001307142,0.0001619187,0.00009800633,0.0002311833,0.0001453842,0.0000580112,0.000002677127],"category_scores_gemma":[0.00007238619,0.00009232129,0.00001195963,0.0004387478,0.0000188075,0.0005081616,0.0001529957,0.0001929073,0.00000108425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007796283,"about_ca_system_score_gemma":0.0003458912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002447622,"about_ca_topic_score_gemma":0.0005219112,"domain_scores_codex":[0.9989644,0.00008624267,0.0002561945,0.0003963964,0.000139994,0.0001567968],"domain_scores_gemma":[0.9994049,0.00009322309,0.00006501062,0.0002959924,0.00009343834,0.0000474017],"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":[0.00001564063,0.0001450986,0.0006251439,0.00004539981,0.000019088,0.00002500674,0.009616723,0.009695414,0.002669409,0.9343258,0.0002838123,0.04253351],"study_design_scores_gemma":[0.0002732559,0.00002440797,0.0001342798,0.00009032406,0.000004129172,0.00001865246,0.0007969195,0.9950096,0.001758448,0.001689138,0.00009330312,0.0001075125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2892794,0.0001693302,0.7032136,0.001429662,0.00009967064,0.0001535114,9.902886e-8,0.00006686577,0.005587887],"genre_scores_gemma":[0.6435479,0.000004278808,0.3554347,0.0006477812,0.00004211119,0.000003126025,0.000004345112,0.000003369833,0.0003123802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853142,"threshold_uncertainty_score":0.3764753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03359465857662799,"score_gpt":0.2908579843163457,"score_spread":0.2572633257397178,"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."}}