{"id":"W2185685412","doi":"10.1080/10691898.2003.11910695","title":"Multiple-Choice Randomization","year":2003,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Randomization; Cheating; Randomized experiment; Computer science; Randomized controlled trial; Sample (material); Mathematics education; Psychology; Statistics; Econometrics; Mathematics; Social psychology; 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":[],"consensus_categories":[],"category_scores_codex":[0.0562896,0.002106974,0.003401625,0.001927215,0.001494995,0.002469744,0.002891417,0.002836664,0.08131513],"category_scores_gemma":[0.2121294,0.00101227,0.0009951338,0.002580016,0.002766787,0.002503244,0.003284787,0.004396563,0.01252878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001510867,"about_ca_system_score_gemma":0.003420511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003334479,"about_ca_topic_score_gemma":0.0007184264,"domain_scores_codex":[0.9000567,0.0770779,0.005608934,0.005716815,0.009036409,0.002503328],"domain_scores_gemma":[0.8469473,0.09739454,0.006814224,0.03494958,0.01127639,0.002618015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.04112221,0.005127931,0.003904697,0.003514212,0.0005385171,0.000482246,0.003473956,0.006700438,0.01006247,0.2769112,0.07854766,0.5696145],"study_design_scores_gemma":[0.04373371,0.01944827,0.005926813,0.00177859,0.0007184172,0.001041319,0.0009670837,0.05498753,0.02161388,0.3595851,0.4895115,0.0006878938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03864663,0.001254904,0.7903708,0.001977936,0.004328846,0.1158572,0.003328508,0.004083893,0.04015137],"genre_scores_gemma":[0.2200767,0.001020319,0.518573,0.002302341,0.00112023,0.2272087,0.00107878,0.0008516046,0.02776827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08131513,"threshold_uncertainty_score":0.2976914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007929292996903231,"score_gpt":0.271504982347463,"score_spread":0.2635756893505597,"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."}}