{"id":"W4391184004","doi":"10.2196/53559","title":"The Temperature Feature of ChatGPT: Modifying Creativity for Clinical Research","year":2024,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Creativity; Feature (linguistics); Consistency (knowledge bases); Preprint; Variable (mathematics); Variety (cybernetics); Data science; Randomness; Interface (matter); Human–computer interaction; Artificial intelligence; Psychology; World Wide Web; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005350968,0.00008538712,0.0001708065,0.0001046588,0.00207899,0.000223911,0.0003516068,0.0003318721,0.00003503379],"category_scores_gemma":[0.00632584,0.00005908531,0.0001383787,0.0005972255,0.0007698563,0.0001507868,0.00003496123,0.0007639786,0.000007375797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002268801,"about_ca_system_score_gemma":0.0006862789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000882181,"about_ca_topic_score_gemma":0.001743008,"domain_scores_codex":[0.9975353,0.0008311807,0.0002642675,0.0002665966,0.0006681566,0.0004345302],"domain_scores_gemma":[0.9853111,0.01390748,0.00006923372,0.0002202366,0.0003432289,0.0001487463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006059559,0.0002711423,0.1969603,0.0006240405,0.00009495293,0.000002074966,0.3797074,4.398101e-7,0.0007385605,0.2219346,0.1577916,0.04181426],"study_design_scores_gemma":[0.000122641,0.0001558644,0.2453502,0.000163004,0.00001145791,7.73012e-8,0.0244301,0.000007502726,0.0001875487,0.007816639,0.7216285,0.0001265059],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838606,0.001070658,0.000001422059,0.006799754,0.004494201,0.002203513,0.00001849681,0.00008139563,0.001470023],"genre_scores_gemma":[0.9947156,0.0002596018,0.00003015939,0.00001873442,0.002650263,0.0008038521,0.00001169159,0.00001754244,0.001492575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5638368,"threshold_uncertainty_score":0.9992202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5350060726704904,"score_gpt":0.6339170265971087,"score_spread":0.0989109539266183,"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."}}