{"id":"W4385080756","doi":"10.2196/47049","title":"The Potential and Concerns of Using AI in Scientific Research: ChatGPT Performance Evaluation","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":186,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Thematic analysis; Context (archaeology); Quality (philosophy); Computer science; Data science; Data quality; Qualitative research; Social science; Engineering; Sociology","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":[],"consensus_categories":[],"category_scores_codex":[0.005074412,0.00004699485,0.00008699115,0.0002908617,0.0003026869,0.0000337714,0.00007746262,0.00009567606,0.00009579021],"category_scores_gemma":[0.001989327,0.00003529382,0.00001630934,0.001044775,0.0004597667,0.0001075925,0.00002942419,0.0002848157,0.00002664764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001555982,"about_ca_system_score_gemma":0.00428653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003894947,"about_ca_topic_score_gemma":0.0001016304,"domain_scores_codex":[0.9980245,0.0001756201,0.0003275271,0.0001810177,0.001065464,0.0002258459],"domain_scores_gemma":[0.9987557,0.0001776044,0.00005841474,0.0001879672,0.0006796015,0.0001407338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007696053,0.0001909179,0.02790361,0.0001518633,0.000004377141,7.042192e-7,0.008500525,0.00002048478,0.00200373,0.0003869766,0.004508797,0.9562511],"study_design_scores_gemma":[0.0002476467,0.0002549744,0.4200614,0.001295979,0.00003059003,0.00003013105,0.03218647,0.5275108,0.004466836,0.005280292,0.008498068,0.0001367566],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822502,0.0003589966,0.000006863853,0.01529305,0.001317313,0.0006415771,3.228868e-7,0.00001195807,0.0001197352],"genre_scores_gemma":[0.9987034,0.0002823435,0.00001697296,0.0001507497,0.0004246072,0.0001326087,0.00003088642,0.000006235992,0.0002521835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9561143,"threshold_uncertainty_score":0.760412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3978155569671569,"score_gpt":0.5939620970070143,"score_spread":0.1961465400398574,"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."}}