{"id":"W4412158470","doi":"10.21203/rs.3.rs-6762129/v1","title":"Generative artificial intelligence models outperform students on divergent and convergent thinking assessments","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Generative grammar; Convergent thinking; Artificial intelligence; Psychology; Mathematics education; Computer science; Cognitive science; Social psychology; Creative thinking; Creativity","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":[0.003807267,0.001383251,0.0007020875,0.000728995,0.0002918947,0.003648397,0.00113916,0.001737933,0.009885767],"category_scores_gemma":[0.02683989,0.0003113725,0.0008302737,0.0004778625,0.0006914314,0.003258366,0.001549687,0.002384374,0.004037284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006410066,"about_ca_system_score_gemma":0.001041392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001764471,"about_ca_topic_score_gemma":0.002016061,"domain_scores_codex":[0.9985494,0.0006095629,0.0001069732,0.0003249418,0.0003457556,0.00006326051],"domain_scores_gemma":[0.971658,0.02000182,0.001682773,0.003902504,0.001205824,0.001549097],"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":[0.009463937,0.009147953,0.1577154,0.001048259,0.001254867,0.00039373,0.003068972,0.181261,0.01710826,0.02639319,0.02814291,0.5650015],"study_design_scores_gemma":[0.001363198,0.006437396,0.06982891,0.0004560204,0.0006799936,0.0003311778,0.00154064,0.7417268,0.02235363,0.1362788,0.01878412,0.0002192813],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9539008,0.0005080892,0.02385723,0.001142713,0.0002826052,0.0001509538,0.0007290898,0.001332832,0.01809572],"genre_scores_gemma":[0.97826,0.000318661,0.009108668,0.00028927,0.00004601609,0.00008837571,0.001384927,0.0001851554,0.01031884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009885767,"threshold_uncertainty_score":0.03307116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3473652930941061,"score_gpt":0.5738697842608843,"score_spread":0.2265044911667782,"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."}}