{"id":"W4414662362","doi":"10.1002/jocb.70072","title":"Exploring the Role of Response Time in Item Response Theory: Rethinking the <scp>PISA</scp> 2022 Creative Thinking Assessment","year":2025,"lang":"en","type":"article","venue":"The Journal of Creative Behavior","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Interpretability; Item response theory; Leverage (statistics); Cognition; Action (physics); Task (project management); Response time","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":[0.02104362,0.0002590842,0.0004354368,0.0004629385,0.0006493002,0.00009201843,0.001385606,0.00007673769,0.0002544099],"category_scores_gemma":[0.004789715,0.0001348299,0.0002002546,0.001228248,0.0008333661,0.0003565282,0.0002188552,0.001254091,0.0000126432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002888077,"about_ca_system_score_gemma":0.0005312145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000930749,"about_ca_topic_score_gemma":0.00001339274,"domain_scores_codex":[0.9851903,0.0126353,0.0008180781,0.0002496442,0.0007334381,0.0003732547],"domain_scores_gemma":[0.9709392,0.02694287,0.0009636143,0.000732013,0.0003587684,0.00006349548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.01219368,0.001977973,0.06378908,0.00001025355,0.000297246,0.00009072408,0.5893831,0.0001397014,0.279879,0.03583644,0.001816712,0.01458609],"study_design_scores_gemma":[0.000663917,0.0005273209,0.8138682,0.0002366572,0.0002759115,0.00009412169,0.1569352,0.0000259177,0.01992772,0.0052057,0.002175631,0.00006371629],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873275,0.0004743515,0.0001981905,0.002398732,0.0006114732,0.0006173247,0.00001520606,0.00001734896,0.008339854],"genre_scores_gemma":[0.989782,0.00009575272,0.00009302289,0.0003341288,0.00006574541,0.0001194547,6.24786e-7,0.0000230283,0.009486181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7500792,"threshold_uncertainty_score":0.7293342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0613947946839882,"score_gpt":0.3830403503972361,"score_spread":0.3216455557132478,"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."}}