{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005857212,0.0003899509,0.001062566,0.009899152,0.00103128,0.002063303,0.0009246392,0.001535696,0.01508611],"category_scores_gemma":[0.09742379,0.0002627925,0.0004262119,0.006000495,0.0004390887,0.001530863,0.002230186,0.0007199744,0.0034407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007387597,"about_ca_system_score_gemma":0.0008249544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001264878,"about_ca_topic_score_gemma":0.002600348,"domain_scores_codex":[0.9909984,0.002869415,0.001349633,0.001079263,0.003311756,0.0003916961],"domain_scores_gemma":[0.9105627,0.05729656,0.01232559,0.004876854,0.0123449,0.002593413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002738097,0.000889826,0.5677499,0.001220702,0.000281666,0.001078879,0.003110188,0.0008393311,0.01244734,0.004498202,0.04134952,0.3637963],"study_design_scores_gemma":[0.0002769211,0.001162113,0.8958158,0.0004439971,0.000253946,0.003070118,0.003647836,0.01349743,0.02139407,0.01135849,0.04896251,0.0001166977],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9653482,0.001149113,0.009346758,0.001158698,0.0002229831,0.0002688667,0.007652991,0.0008711854,0.0139811],"genre_scores_gemma":[0.9660235,0.0003724485,0.01655638,0.0002009155,0.0002694435,0.0001324835,0.00872709,0.0001789393,0.007538727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9984643,"threshold_uncertainty_score":0.05046809,"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."}}