{"id":"W4327910164","doi":"10.1177/01466216231165299","title":"Confidence Screening Detector: A New Method for Detecting Test Collusion","year":2023,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Collusion; Cheating; Clique; Computer science; Test (biology); Detector; Item response theory; Scale (ratio); Statistical hypothesis testing; Variable (mathematics); Similarity (geometry); Selection (genetic algorithm); Statistics; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics; Psychology; Psychometrics; Social psychology","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03331906,0.0003457165,0.0006634211,0.0006293374,0.000612844,0.0003055469,0.001401497,0.0002542401,0.0002864282],"category_scores_gemma":[0.164273,0.0002420383,0.000264477,0.004983244,0.00007605721,0.00008341152,0.0003016013,0.0003694257,0.0003126585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008949154,"about_ca_system_score_gemma":0.00004891637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002896103,"about_ca_topic_score_gemma":0.0000133815,"domain_scores_codex":[0.992996,0.000430983,0.001227693,0.001547457,0.002879223,0.0009186168],"domain_scores_gemma":[0.9471056,0.05022569,0.0006227305,0.001074937,0.0005475571,0.0004234133],"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":[0.0001923013,0.0000743027,0.001822662,0.00000748797,0.00002354739,0.000005889927,0.0001326055,0.0002920153,0.09936117,0.001519588,0.01807573,0.8784927],"study_design_scores_gemma":[0.006413399,0.002106312,0.2654065,0.000169571,0.0001016738,0.00006194335,0.003065366,0.01402223,0.02420528,0.5928633,0.08991892,0.001665497],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01494691,0.0001297608,0.9746787,0.0009962765,0.000871349,0.00121214,0.000009984331,0.0005918519,0.006563029],"genre_scores_gemma":[0.6095884,0.000009999426,0.3889287,0.0007185371,0.0003053276,0.0002098776,0.00000143718,0.00002423615,0.0002134434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8768272,"threshold_uncertainty_score":0.9954014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7210023253769497,"score_gpt":0.531043618285663,"score_spread":0.1899587070912867,"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."}}