{"id":"W4319598807","doi":"10.3390/a16020089","title":"Rapid Guessing in Low-Stakes Assessments: Finding the Optimal Response Time Threshold with Random Search and Genetic Algorithm","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Flagging; Computer science; Response time; Algorithm; Threshold model; Machine learning","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":[0.008623094,0.0009904305,0.001533094,0.002959326,0.0005245208,0.001574642,0.00172283,0.001818525,0.0008716596],"category_scores_gemma":[0.04838538,0.0006407187,0.0008808391,0.001141833,0.001163063,0.001670212,0.001128958,0.001551071,0.0003227696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00136479,"about_ca_system_score_gemma":0.001981791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004946467,"about_ca_topic_score_gemma":0.004607535,"domain_scores_codex":[0.9945083,0.003330313,0.0003058318,0.0009801243,0.0006789385,0.0001964261],"domain_scores_gemma":[0.9634437,0.03072535,0.002313206,0.001273906,0.001840494,0.0004032674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001010537,0.0007671746,0.03930184,0.000364452,0.0003613995,0.0001909465,0.0007184591,0.5827817,0.01678131,0.01110757,0.001093015,0.3455215],"study_design_scores_gemma":[0.00006606952,0.0001267211,0.002730196,0.00002970846,0.00002395982,0.00005256024,0.00005832889,0.989013,0.003247305,0.004408446,0.0002081631,0.00003557191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1690812,0.0002003705,0.8277574,0.0002176341,0.00002332762,0.0003128949,0.00006678764,0.001182059,0.001158323],"genre_scores_gemma":[0.4580063,0.00006721629,0.5407249,0.0001222531,0.0000115214,0.0004152546,0.00013821,0.000107575,0.0004068025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008623094,"threshold_uncertainty_score":0.04560381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1531013219795476,"score_gpt":0.3784307984303121,"score_spread":0.2253294764507645,"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."}}