{"id":"W2983081523","doi":"10.1111/jocd.13201","title":"Online comment‐based prediction of cosmetic ingredient's sensory irritation using gradient boosting algorithm","year":2019,"lang":"en","type":"article","venue":"Journal of Cosmetic Dermatology","topic":"Advancements in Transdermal Drug Delivery","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Boosting (machine learning); Cosmetics; Ingredient; Irritation; Sensory system; Context (archaeology); Artificial intelligence; Gradient boosting; Computer science; Skin irritation; Machine learning; Medicine; Algorithm; Dermatology; Biology; Random forest; Pathology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007026367,0.0002646393,0.0007098,0.0005523217,0.0001266552,0.00000977154,0.0003005267,0.0002916135,0.0002860642],"category_scores_gemma":[0.0001612776,0.0002641156,0.0002105754,0.0002977538,0.0002850545,0.0002441642,0.00005495312,0.0009727003,0.00001717741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001922565,"about_ca_system_score_gemma":0.0001853911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006261349,"about_ca_topic_score_gemma":0.000001491625,"domain_scores_codex":[0.9965463,0.0008910513,0.00147096,0.0002279096,0.0004064004,0.0004573272],"domain_scores_gemma":[0.9966948,0.0009894443,0.001332348,0.0001995869,0.0005892479,0.0001945791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003926263,0.01090049,0.2354334,0.002295579,0.003774855,0.002068535,0.004749426,0.2623875,0.3124587,0.001126708,0.006578769,0.1542997],"study_design_scores_gemma":[0.01611688,0.0015582,0.00774812,0.0005699787,0.001802981,0.004582813,0.001920515,0.8575857,0.07163265,0.00119264,0.03466781,0.0006217542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9407046,0.001104222,0.05213081,0.001156174,0.004024948,0.0004628726,0.0001758101,0.00002887965,0.0002116509],"genre_scores_gemma":[0.9745114,0.0001830551,0.02274279,0.002310422,0.0001389349,0.000003600662,0.00004252403,0.00003402655,0.0000332177],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5951982,"threshold_uncertainty_score":0.9999811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.117791725885851,"score_gpt":0.4173502534906133,"score_spread":0.2995585276047624,"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."}}