{"id":"W2001217603","doi":"10.1080/02664760050120588","title":"Detecting excessive similarity in answers on multiple choice exams","year":2000,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Cheating; False accusation; Bonferroni correction; Simple (philosophy); Computer science; Econometrics; Similarity (geometry); Statistics; Mathematics; Artificial intelligence; Psychology; Social psychology; Epistemology","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":[],"consensus_categories":[],"category_scores_codex":[0.001496302,0.00009904635,0.0002187742,0.00009315489,0.000260712,0.00004506846,0.0002551801,0.0003198166,0.0004984227],"category_scores_gemma":[0.002053487,0.00009284901,0.00003519063,0.0002018591,0.0001327733,0.0001067642,0.000008537924,0.00180717,0.00002304492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001738341,"about_ca_system_score_gemma":0.0001781315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007999705,"about_ca_topic_score_gemma":0.001893631,"domain_scores_codex":[0.9985365,0.000128117,0.0004232738,0.0001106402,0.0005213401,0.0002800821],"domain_scores_gemma":[0.9963887,0.003045793,0.0002838135,0.00006451561,0.00009147761,0.0001257369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00120146,0.0004260921,0.01944984,0.00005750421,0.00009737416,0.0003213067,0.0971502,0.009136831,0.0006278098,0.05062998,0.01837601,0.8025256],"study_design_scores_gemma":[0.00764833,0.0009213325,0.09757487,0.0006032636,0.0001975556,0.00003780781,0.06617571,0.007829263,0.003419595,0.1781055,0.6357927,0.001694071],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8959935,0.00004765583,0.008348178,0.0006624587,0.0004592636,0.0002372186,0.00008236842,0.00002109566,0.09414823],"genre_scores_gemma":[0.9918231,0.0002024911,0.006787441,0.0005306621,0.0004521057,0.000001419328,0.000001866547,0.000008354255,0.0001925612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8008315,"threshold_uncertainty_score":0.7851356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02290021767480872,"score_gpt":0.3088394722427678,"score_spread":0.285939254567959,"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."}}