{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001215744,0.0002587223,0.0003544976,0.000166971,0.0003525325,0.0001142845,0.0002700246,0.0001416505,0.0004818758],"category_scores_gemma":[0.00002763716,0.000153006,0.00005765433,0.0008051151,0.0003532693,0.0000900549,0.0001387174,0.0004467743,0.0003280854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003597152,"about_ca_system_score_gemma":0.00002128622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001195444,"about_ca_topic_score_gemma":0.000005996936,"domain_scores_codex":[0.9976261,0.0004941215,0.0003133641,0.000564018,0.000327898,0.0006745151],"domain_scores_gemma":[0.9988469,0.0006052293,0.00005624168,0.0003317386,0.00006444492,0.00009541511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003687745,0.0004549918,0.02264232,0.000018369,0.0002723805,0.002731466,0.006561119,0.0003109978,0.0006132209,0.00003712803,0.004008304,0.958662],"study_design_scores_gemma":[0.007128773,0.00124209,0.9694469,0.0001574179,0.00007392909,0.0001727754,0.005277598,0.01201926,0.00008229408,0.0001191561,0.003682964,0.0005968147],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944248,0.001427405,0.001039831,0.000949272,0.0003668964,0.0005241754,0.00003164819,0.0001429249,0.001093116],"genre_scores_gemma":[0.9728517,0.0006007808,0.01450839,0.0006564477,0.0006187105,0.0004848432,0.00004825663,0.0001208877,0.01011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9580652,"threshold_uncertainty_score":0.6239405,"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."}}