{"id":"W4389480085","doi":"10.17849/insm-50-2-1-4.1","title":"ChatGPT: How Closely Should We Be Watching?","year":2023,"lang":"en","type":"article","venue":"Journal of Insurance Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"cons; Psychology; Engineering ethics; Computer science; Engineering; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001421278,0.0001580923,0.0005445518,0.0004197126,0.0001095291,0.00001290759,0.0001585369,0.0001250433,0.0001612512],"category_scores_gemma":[0.00153704,0.0001035461,0.0001277626,0.0008032193,0.000151049,0.0001946158,0.00001576289,0.0006364432,0.00005323024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001055806,"about_ca_system_score_gemma":0.0002690485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008469125,"about_ca_topic_score_gemma":0.00001839742,"domain_scores_codex":[0.9979073,0.00006194854,0.0007509293,0.0001533701,0.000796587,0.0003298048],"domain_scores_gemma":[0.9980451,0.0003296603,0.0004283978,0.0002336207,0.0006467114,0.000316459],"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":[0.0009318247,0.0002761117,0.1830286,0.0007490675,0.0001973565,0.0008632086,0.02699615,0.00005232846,0.02341819,0.0004136781,0.366944,0.3961295],"study_design_scores_gemma":[0.001709631,0.006890232,0.2826214,0.007348055,0.0003473319,0.003064998,0.03397233,0.0007981638,0.02989361,0.008839659,0.6239477,0.0005668659],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6466995,0.001849764,0.0001479109,0.3483415,0.0022731,0.0001387295,0.000002182872,0.00003886205,0.0005084459],"genre_scores_gemma":[0.983049,0.00686223,0.0002083532,0.0038489,0.004263401,0.000004882581,0.000007683709,0.00002548482,0.001730005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3955626,"threshold_uncertainty_score":0.4222488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.303753428389547,"score_gpt":0.4585329477014499,"score_spread":0.1547795193119029,"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."}}