{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007594911,0.0009653773,0.001491888,0.004691035,0.0008421253,0.001552616,0.002776377,0.001654523,0.00238728],"category_scores_gemma":[0.04269982,0.0005114629,0.0009504157,0.002315692,0.001248643,0.001839786,0.002968826,0.001660425,0.0006566626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008657331,"about_ca_system_score_gemma":0.002068877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001883643,"about_ca_topic_score_gemma":0.001837345,"domain_scores_codex":[0.993534,0.002475905,0.0004363583,0.001064892,0.002192798,0.0002960799],"domain_scores_gemma":[0.9699812,0.02120539,0.002454741,0.001966643,0.003597509,0.0007945159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008666341,0.0005146192,0.03174175,0.000289828,0.0003988839,0.0003215641,0.0004132217,0.04259134,0.01544987,0.02067313,0.004297736,0.8824415],"study_design_scores_gemma":[0.0001217502,0.0003573005,0.008672311,0.00004149633,0.00008734166,0.0006861259,0.00008110157,0.963706,0.008776341,0.01452353,0.002849716,0.00009697982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02439375,0.0001615797,0.9734673,0.0001699518,0.0000653062,0.0002458928,0.0001074317,0.000677355,0.0007114435],"genre_scores_gemma":[0.279286,0.0001150824,0.718148,0.0001781129,0.00008714262,0.0004804078,0.0003327878,0.000095018,0.001277454],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007594911,"threshold_uncertainty_score":0.0401662,"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."}}