{"id":"W4313892552","doi":"10.1007/978-3-031-21796-8_9","title":"Examining the Problem of Fraudulent English Test Scores: What Can Canadian Higher Education Institutions Learn?","year":2023,"lang":"en","type":"book-chapter","venue":"Ethics and integrity in educational contexts","topic":"Legal Issues in Education","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Test (biology); Mathematics education; Political science; Psychology; Computer science; Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002545819,0.0002405548,0.000266576,0.0004104107,0.0009344504,0.0003518531,0.0004819471,0.0008229589,0.0006053575],"category_scores_gemma":[0.003495444,0.0002218542,0.00006123037,0.000221914,0.001278319,0.0004457104,0.00006257236,0.003338126,0.00003800692],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113857,"about_ca_system_score_gemma":0.02808769,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3283324,"about_ca_topic_score_gemma":0.78803,"domain_scores_codex":[0.9978899,0.0002496188,0.0005067725,0.0004093115,0.0006377035,0.0003066598],"domain_scores_gemma":[0.9944034,0.003172311,0.0002999227,0.0003068862,0.001572425,0.0002450056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001491784,0.00006795192,0.00249548,0.00005470921,0.00001801298,2.654805e-7,0.1170787,0.000003147961,6.878929e-7,0.8713403,0.004912565,0.004026688],"study_design_scores_gemma":[0.00006664621,0.00003331683,0.0180352,0.001709027,0.00003004959,6.304936e-7,0.02367399,7.673656e-7,0.000001198048,0.1866479,0.7695488,0.000252476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.004565513,0.004573314,6.858035e-7,0.1330545,0.009116121,0.00114706,0.0001460032,0.00004275522,0.8473541],"genre_scores_gemma":[0.5979554,0.003971888,0.0001365708,0.001514756,0.001823023,0.0001390963,0.0002459801,0.00003357638,0.3941797],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7646363,"threshold_uncertainty_score":0.9989612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1476693810680676,"score_gpt":0.3840590912020521,"score_spread":0.2363897101339845,"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."}}