{"id":"W4398519193","doi":"10.7910/dvn/4yhosk/rquvm7","title":"2018 Larkin et al Supplementary Material CCS expert elicitation_risk assessment issues.pdf","year":2019,"lang":"en","type":"dataset","venue":"Bristol Research (University of Bristol)","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Ottawa","funders":"","keywords":"Expert elicitation; Environmental science; Computer science; Mathematics; Statistics","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01110406,0.0004820039,0.001460061,0.002429419,0.0009211448,0.0004511663,0.004850772,0.000460364,0.05143468],"category_scores_gemma":[0.0007691137,0.0005257361,0.0006972161,0.002039292,0.001030009,0.0007187611,0.002110752,0.001345932,0.006774989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007875098,"about_ca_system_score_gemma":0.001315557,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06773552,"about_ca_topic_score_gemma":0.01350238,"domain_scores_codex":[0.9847861,0.003475386,0.001027185,0.001655512,0.008122371,0.0009334792],"domain_scores_gemma":[0.9925577,0.001638504,0.0009702003,0.002553462,0.001817239,0.0004628623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003987844,0.0003495792,0.0001430553,0.00003777263,0.0002245402,0.0002516319,0.0002963863,0.00003679912,0.00008119306,0.00004543515,0.9947484,0.00338638],"study_design_scores_gemma":[0.001019087,0.0003541286,0.000865391,0.00007445117,0.00008470382,0.00001022435,0.008587699,0.0003661854,0.00001431879,0.0006537047,0.9874784,0.0004916456],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001478623,0.0002941508,0.0008798913,0.02521849,0.000900969,0.0007351095,0.9695728,0.00001994581,0.000900008],"genre_scores_gemma":[0.0006273624,0.01105656,0.003014097,0.0009626178,0.0001829153,0.000004094199,0.9673751,0.00003568499,0.01674159],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05423314,"threshold_uncertainty_score":0.9997194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1736326266491328,"score_gpt":0.4814716276163497,"score_spread":0.3078390009672168,"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."}}