{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1904074,0.00284378,0.005344039,0.00267012,0.002345183,0.004408192,0.003030934,0.006379492,0.01453522],"category_scores_gemma":[0.2721562,0.001904888,0.003810254,0.002277361,0.005623995,0.005890636,0.002854124,0.005395348,0.001779193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003204766,"about_ca_system_score_gemma":0.007304403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006598696,"about_ca_topic_score_gemma":0.0007444875,"domain_scores_codex":[0.6877508,0.2838281,0.01108145,0.007138454,0.008236095,0.00196512],"domain_scores_gemma":[0.6588952,0.2917467,0.01569216,0.02193667,0.008362764,0.003366552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.6421258,0.02911138,0.002747062,0.03023256,0.008944397,0.0003211256,0.002908339,0.01076824,0.004706605,0.04701377,0.00903063,0.2120901],"study_design_scores_gemma":[0.8039482,0.08846476,0.001999121,0.004329104,0.00335733,0.0001153788,0.0003659237,0.03330196,0.004136791,0.04336414,0.01635834,0.0002590324],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.08739172,0.003644175,0.3229463,0.003204881,0.006772553,0.564814,0.001308396,0.002608781,0.007309232],"genre_scores_gemma":[0.1958773,0.0004816303,0.3080918,0.002004959,0.0006496545,0.4913698,0.0001965348,0.0001136275,0.00121469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1904074,"threshold_uncertainty_score":0.9983718,"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."}}