{"id":"W4393181773","doi":"10.1007/s10639-024-12633-y","title":"AI-experiments in education: An AI-driven randomized controlled trial for higher education research","year":2024,"lang":"en","type":"article","venue":"Education and Information Technologies","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"University of Adelaide","keywords":"Randomized controlled trial; Psychological intervention; Computer science; Test (biology); Intervention (counseling); Process (computing); Psychology; Educational technology; Medical education; Control (management); Randomized experiment; Applied psychology; Artificial intelligence; Knowledge management; Mathematics education; Medicine","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001137382,0.0001694173,0.0003632286,0.001789001,0.000207711,0.001379994,0.0003035019,0.0001937647,0.0002119116],"category_scores_gemma":[0.0008223729,0.0001336095,0.00007281765,0.0009892107,0.0001816684,0.009734381,0.00009295518,0.0002510317,0.0001403313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009556537,"about_ca_system_score_gemma":0.0008098384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001893134,"about_ca_topic_score_gemma":0.000008805873,"domain_scores_codex":[0.9985999,0.00003277915,0.0006529803,0.0002360747,0.0002604997,0.0002177101],"domain_scores_gemma":[0.9986512,0.000143316,0.0001708195,0.000289426,0.0007327577,0.00001247644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.02951334,0.0004528907,0.00004907377,0.0003002381,0.00001866096,2.659727e-8,0.0002561615,0.000003415491,0.00001821324,0.6485208,0.06965741,0.2512098],"study_design_scores_gemma":[0.09220941,0.000034068,0.0000940744,0.0002511911,0.00003330419,0.000001161016,0.00586564,0.003043134,0.0001339062,0.05520298,0.8429025,0.0002286539],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4040008,0.02509773,0.005676728,0.3033394,0.07029602,0.0503128,0.00003920165,0.005549567,0.1356877],"genre_scores_gemma":[0.9822401,0.0004628796,0.0005821268,0.003798063,0.001149758,0.008743268,0.0006185826,0.00001707782,0.002388178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7732451,"threshold_uncertainty_score":0.9996567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07164085073398631,"score_gpt":0.4069752234615291,"score_spread":0.3353343727275428,"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."}}