{"id":"W4317181638","doi":"10.1289/isee.2022.o-op-091","title":"Integrating biological knowledge in Kernel-based analyses of environmental mixtures and health","year":2022,"lang":"en","type":"article","venue":"ISEE Conference Abstracts","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Prior probability; Computer science; Set (abstract data type); Flexibility (engineering); Bayesian probability; Index (typography); Parametric statistics; Data mining; Function (biology); Machine learning; Statistics; Artificial intelligence; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0007433282,0.000139305,0.0003662679,0.00009923954,0.0000881056,0.00001798103,0.0001573553,0.00004509692,0.0005732076],"category_scores_gemma":[0.0003996116,0.0001136395,0.0000492684,0.0001099697,0.0001552662,0.0000321488,0.00009890219,0.0002917237,0.000002014021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006066918,"about_ca_system_score_gemma":0.0001556153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001281207,"about_ca_topic_score_gemma":0.00006460594,"domain_scores_codex":[0.9986052,0.0002892603,0.0004867738,0.0002515518,0.0001482972,0.0002189249],"domain_scores_gemma":[0.9983985,0.001121606,0.0002272492,0.0001500652,0.00001514794,0.00008745859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002611355,0.004041108,0.02597332,0.0008045418,0.000130075,0.0001335812,0.005514328,0.0006821335,0.08708067,0.4114709,0.00070832,0.4631999],"study_design_scores_gemma":[0.001189219,0.0009986133,0.6075544,0.0002483284,0.00003235907,0.00001772799,0.003258196,0.002797879,0.008194554,0.3750351,0.0001901558,0.0004834678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9627715,0.0004699166,0.03433317,0.0002139459,0.00006216572,0.0002543493,0.0001553457,0.000026066,0.001713598],"genre_scores_gemma":[0.9243934,0.00002016269,0.07544411,0.0000781832,0.00001024833,0.00002429591,0.0000099409,0.000006951916,0.0000126905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5815811,"threshold_uncertainty_score":0.6276221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2272289502377228,"score_gpt":0.4444028201480957,"score_spread":0.2171738699103729,"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."}}