{"id":"W7117478841","doi":"10.1007/s00146-025-02816-7","title":"How to maximize the creativity of artificial intelligence: an experimental analysis of response order and prompting effects","year":2025,"lang":"en","type":"article","venue":"AI & Society","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; McGill University; McMaster University; University of Waterloo; University of Toronto","funders":"","keywords":"Originality; Creativity; Task (project management); Value (mathematics); Chatbot; Affect (linguistics); Contrast (vision)","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":[0.01090318,0.001359281,0.001322732,0.0006709142,0.0005052136,0.00310514,0.001745037,0.001480352,0.007856194],"category_scores_gemma":[0.1141599,0.001036677,0.0005317828,0.0005901474,0.001651241,0.003630044,0.001411706,0.002673464,0.0007829645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005840806,"about_ca_system_score_gemma":0.00125839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004952486,"about_ca_topic_score_gemma":0.0003398568,"domain_scores_codex":[0.994449,0.002706423,0.0006758432,0.001011588,0.0008642562,0.0002929635],"domain_scores_gemma":[0.8070875,0.1741142,0.006959022,0.008486354,0.001479159,0.001873619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.1372245,0.02993794,0.01239748,0.003126249,0.0006796152,0.0004130205,0.005988882,0.02097007,0.5422783,0.02843188,0.001655209,0.2168969],"study_design_scores_gemma":[0.05000935,0.09194734,0.1493296,0.0006996758,0.00244318,0.001342263,0.00276659,0.2035661,0.3772214,0.1107551,0.009045333,0.0008742378],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9826695,0.000220205,0.01136833,0.0002149231,0.0001834811,0.0006987739,0.0001211329,0.0001812313,0.004342545],"genre_scores_gemma":[0.9721871,0.0001799838,0.02366129,0.0002165727,0.00009643914,0.001187895,0.000113679,0.0003060901,0.002050854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01090318,"threshold_uncertainty_score":0.05766219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04193075441254213,"score_gpt":0.4154233292991405,"score_spread":0.3734925748865984,"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."}}