{"id":"W4387902147","doi":"10.1093/eurpub/ckad160.1237","title":"ChatGPT for Systematic and Scoping Reviews in Public Health Research: An Applicable Approach","year":2023,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Systematic review; Computer science; CLARITY; Data science; Management science; Information retrieval; Knowledge management; MEDLINE; Engineering","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":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5834292,0.0001494973,0.0009285437,0.002636852,0.0006529325,0.002010942,0.001829728,0.00001767298,0.00001259946],"category_scores_gemma":[0.02102841,0.0001021427,0.00009841784,0.004560372,0.0001153726,0.0009435652,0.0005529053,0.0004060677,0.0001240628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002076193,"about_ca_system_score_gemma":0.0009811267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000206174,"about_ca_topic_score_gemma":0.00002784146,"domain_scores_codex":[0.9187819,0.06202023,0.008395727,0.001946557,0.005680894,0.003174732],"domain_scores_gemma":[0.9937442,0.001670314,0.00163213,0.001133596,0.0006121069,0.001207684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005936785,0.0003497,0.0005235259,0.01238954,0.00001954645,0.0000233452,0.01273319,0.0000974551,0.000004046613,0.00602727,0.1927257,0.7751008],"study_design_scores_gemma":[0.003075094,0.002684338,0.01669027,0.02160129,0.000005863992,0.0002256657,0.04744411,0.05606307,5.61124e-7,0.00323189,0.8483963,0.0005815541],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02505766,0.008736565,0.845935,0.1057245,0.001576787,0.007523955,0.00003141405,0.0001484946,0.00526563],"genre_scores_gemma":[0.9215178,0.003673217,0.06262968,0.006136971,0.001628487,0.0001428363,0.00008329895,0.0001548468,0.00403279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8964602,"threshold_uncertainty_score":0.999025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8696849936256661,"score_gpt":0.5609590718022182,"score_spread":0.3087259218234479,"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."}}