{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00818145,0.001665151,0.0009463491,0.003958828,0.0006952775,0.00234101,0.001985413,0.001664162,0.004609161],"category_scores_gemma":[0.01621864,0.0005311478,0.001880213,0.001921501,0.000451875,0.001991853,0.001358058,0.002083154,0.00549943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0014869,"about_ca_system_score_gemma":0.001999062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02453632,"about_ca_topic_score_gemma":0.02116841,"domain_scores_codex":[0.9975479,0.001053052,0.0002038451,0.0005670772,0.000489603,0.0001385173],"domain_scores_gemma":[0.9914983,0.004963892,0.0003336245,0.0007305102,0.002306493,0.0001671718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004241847,0.001360756,0.036713,0.0004042264,0.000627247,0.000129459,0.0001021753,0.350237,0.002659211,0.00165032,0.02525194,0.5804406],"study_design_scores_gemma":[0.0000150354,0.00008656974,0.00247425,0.00005315518,0.00004664741,0.00002244901,0.00003264481,0.9930356,0.001804471,0.0009010156,0.001513779,0.00001436928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.314875,0.006002156,0.6113486,0.003218549,0.001011899,0.001696836,0.02087386,0.01778809,0.0231851],"genre_scores_gemma":[0.5908179,0.001978682,0.3625526,0.000670007,0.0002768029,0.001072401,0.03069472,0.0005764799,0.01136044],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02453632,"threshold_uncertainty_score":0.048787,"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."}}