{"id":"W4400977208","doi":"10.1007/978-3-031-65996-6_7","title":"Comparative Performance of GPT-4, RAG-Augmented GPT-4, and Students in MOOCs","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Computer science; Multimedia","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001347568,0.0003313987,0.0004732641,0.0006887607,0.0005751366,0.001736889,0.0007401578,0.0008873063,0.006009819],"category_scores_gemma":[0.008937059,0.0001335277,0.0003746736,0.0004164607,0.0003472173,0.0011089,0.00172406,0.0009195585,0.002472855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000663311,"about_ca_system_score_gemma":0.001078125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01000379,"about_ca_topic_score_gemma":0.01173672,"domain_scores_codex":[0.9991615,0.0002092806,0.00004769103,0.0001638664,0.000166789,0.0002510421],"domain_scores_gemma":[0.9935732,0.001932939,0.0003795695,0.0003852303,0.0009587215,0.002770269],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02244994,0.02027854,0.4623134,0.0004768325,0.000470898,0.0008771169,0.01906628,0.01033217,0.007551034,0.00364067,0.0209057,0.4316374],"study_design_scores_gemma":[0.0005740998,0.02821127,0.905174,0.0001989785,0.0003709123,0.0003846293,0.01927247,0.01461133,0.007780734,0.002865024,0.02040484,0.0001515661],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959919,0.0001059045,0.00008780287,0.0000889681,0.00002979157,0.00001284607,0.0001790009,0.00005365337,0.00345025],"genre_scores_gemma":[0.9919422,0.00008534007,0.0001554955,0.00003873953,0.0000112298,0.00002026415,0.000369547,0.00001708907,0.007360209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9986525,"threshold_uncertainty_score":0.02010483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0499225043097927,"score_gpt":0.3260830684011841,"score_spread":0.2761605640913914,"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."}}