{"id":"W6907604018","doi":"10.23645/epacomptox.27625644","title":"Predicting Chemical Occurrence in Environmental and Biological Media: Development and Validation of Machine Learning Models","year":2024,"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":"Presentation (obstetrics); Identification (biology); Statistical learning; Support vector machine; Model validation","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":[],"category_scores_codex":[0.0003929968,0.0004720186,0.0004187069,0.0004022985,0.0000591283,0.0000225468,0.0001104636,0.0004697676,0.001275706],"category_scores_gemma":[0.00002949238,0.0004582679,0.00005104464,0.00009398307,0.0003621897,0.0001291302,0.0003681047,0.0008251965,0.0004194005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003513244,"about_ca_system_score_gemma":0.00001291823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000772752,"about_ca_topic_score_gemma":0.00001047515,"domain_scores_codex":[0.9976167,0.0001714144,0.0005751548,0.000904011,0.0004277072,0.0003049836],"domain_scores_gemma":[0.9993441,0.0000260952,0.0003540432,0.0001573295,8.114836e-7,0.0001176993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003630742,0.00163478,0.1262402,0.001525112,0.0004736642,0.0001094239,0.01126944,0.0005205597,0.7549435,0.00004399407,0.0008369812,0.1020392],"study_design_scores_gemma":[0.01948723,0.003046811,0.1124353,0.009263415,0.001381784,0.001707532,0.006657475,0.1091818,0.5618657,0.006955475,0.151772,0.01624549],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838576,0.007952671,0.0004266944,0.000008943861,0.000175987,0.001813965,0.0007595852,0.0002840311,0.004720561],"genre_scores_gemma":[0.9944513,0.001115709,0.0007497621,0.000003649537,0.00006368638,0.0002182732,0.0006209422,0.0002926479,0.002484056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1930778,"threshold_uncertainty_score":0.9997869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03245891624180328,"score_gpt":0.2190327718545082,"score_spread":0.1865738556127049,"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."}}