{"id":"W6944971056","doi":"10.23645/epacomptox.28507007","title":"Categorical Machine Learning for Predicting Caco-2 Permeability in High Throughput Toxicokinetics","year":2025,"lang":"en","type":"other","venue":"U.S. Environmental Protection Agency","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Categorical variable; Throughput; Predictive modelling; Permeability (electromagnetism); Toxicokinetics; Training set","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005552726,0.0007241137,0.0006610923,0.0005330551,0.0002482908,0.00004173738,0.0003227837,0.0008074923,0.008113408],"category_scores_gemma":[0.0002408239,0.0007860418,0.0002501831,0.0003080113,0.0002034989,0.0001043925,0.0002763654,0.001414546,0.0009798278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001870644,"about_ca_system_score_gemma":0.00006462535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003826461,"about_ca_topic_score_gemma":0.0006773841,"domain_scores_codex":[0.9962725,0.0004021116,0.0007540983,0.001343734,0.0005493374,0.0006782259],"domain_scores_gemma":[0.9986936,0.0000630864,0.0005231235,0.000590169,0.000006552529,0.0001234551],"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":[0.003507148,0.01801596,0.2919959,0.01055829,0.00261479,0.0003031185,0.005603612,0.04869795,0.1956099,0.00162869,0.1161707,0.3052939],"study_design_scores_gemma":[0.007711243,0.001712732,0.0669358,0.0005905628,0.0005236852,0.00005502368,0.0003424203,0.03918749,0.004105147,0.003176356,0.872202,0.003457581],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.053515,0.01067578,0.221678,0.0008763677,0.008130696,0.06547374,0.008032971,0.008206421,0.6234111],"genre_scores_gemma":[0.6760604,0.0003226688,0.001288113,0.00003549957,0.0005601449,0.001733919,0.0008789685,0.001212082,0.3179082],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7560313,"threshold_uncertainty_score":0.999798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01400413175308943,"score_gpt":0.2358063256844366,"score_spread":0.2218021939313472,"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."}}