{"id":"W4365458920","doi":"10.1016/j.yrtph.2023.105388","title":"Artificial intelligence and real-world data for drug and food safety – A regulatory science perspective","year":2023,"lang":"en","type":"article","venue":"Regulatory Toxicology and Pharmacology","topic":"Law, AI, and Intellectual Property","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Food Inspection Agency","funders":"U.S. Food and Drug Administration","keywords":"Regulatory science; Summit; Globe; Political science; Big data; Business; Engineering ethics; Public relations; Computer science; Engineering; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002109902,0.0002411881,0.0003889469,0.0004280776,0.0009212899,0.00009738375,0.001060998,0.0001162055,0.00003665402],"category_scores_gemma":[0.000149455,0.0002172074,0.00003250027,0.0009031178,0.004145665,0.0007261253,0.001647138,0.0002392978,0.00001033433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001068499,"about_ca_system_score_gemma":0.0003665548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002680323,"about_ca_topic_score_gemma":0.0002356573,"domain_scores_codex":[0.9972505,0.0002325893,0.0003670956,0.001316673,0.0001820396,0.0006510946],"domain_scores_gemma":[0.9979517,0.0008386081,0.0001302874,0.0006227468,0.0001782998,0.000278384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003642134,0.0001500829,0.0005552408,0.00009626705,0.0001585704,0.00001758349,0.004475086,0.00003485394,0.04469472,0.8681067,0.01905692,0.06228974],"study_design_scores_gemma":[0.001627304,0.003551262,0.03809946,0.00005651906,0.0002743316,0.0002648509,0.002228736,0.4760117,0.1276284,0.2907507,0.05764252,0.001864338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647324,0.001616467,0.01624637,0.01099181,0.002443694,0.001451683,0.000106085,0.0004986546,0.001912796],"genre_scores_gemma":[0.9956569,0.0007062307,0.00165743,0.001125682,0.0002798522,0.00004515929,0.000006965579,0.00001679287,0.0005049513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5773561,"threshold_uncertainty_score":0.9985645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09511101012148374,"score_gpt":0.3539455784988257,"score_spread":0.258834568377342,"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."}}