{"id":"W4403888260","doi":"10.1007/s10648-024-09965-z","title":"Effectiveness of Unproctored vs. Teacher-Proctored Exams in Reducing Students’ Cheating: A Double-Blind Randomized Controlled Field Experimental Study","year":2024,"lang":"en","type":"article","venue":"Educational Psychology Review","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ministry of Education of the People's Republic of China","keywords":"Cheating; Psychology; Educational psychology; Randomized controlled trial; Mathematics education; Medical education; Pedagogy; Social psychology; Medicine; Internal 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01662549,0.0001967451,0.001370316,0.000174154,0.0001293482,0.00004365401,0.0004757017,0.0003328034,0.001049015],"category_scores_gemma":[0.002338952,0.0001557935,0.0002817711,0.0005488062,0.0002524137,0.0001538634,0.00003771433,0.0009271105,0.00003306596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001520626,"about_ca_system_score_gemma":0.0004021127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00116653,"about_ca_topic_score_gemma":0.00003231805,"domain_scores_codex":[0.9937951,0.003996296,0.0009434512,0.0004905783,0.0005156592,0.000258914],"domain_scores_gemma":[0.9952115,0.004179705,0.0002181331,0.000199184,0.000112762,0.00007874036],"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":[0.5777747,0.0205804,0.06547148,0.008081137,0.00358313,0.00003371838,0.2148397,0.000008741709,0.001671613,0.06806286,0.03219325,0.007699302],"study_design_scores_gemma":[0.9140004,0.001127585,0.01620547,0.03258146,0.001275742,0.00002949479,0.01492873,0.00003548768,0.0006169454,0.008071528,0.009876765,0.001250417],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.847679,0.1201505,0.00003089401,0.0111236,0.002102215,0.008511495,0.000001654826,0.00004059139,0.0103601],"genre_scores_gemma":[0.9913778,0.004332018,0.00005766388,0.0006271133,0.0003661666,0.002482444,0.00001624552,0.00001332644,0.0007271756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3362257,"threshold_uncertainty_score":0.9998642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06871598428386531,"score_gpt":0.4914667452644974,"score_spread":0.422750760980632,"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."}}