{"id":"W1594285860","doi":"","title":"The Most Dangerous Model: A Natural Benchmark for Assessing Model Risk","year":2015,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Natural (archaeology); Computer science; Risk analysis (engineering); Business; Geography; Cartography","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01979982,0.0002077067,0.0003374798,0.0001909698,0.001611304,0.001059122,0.001377647,0.00009903485,0.000002863667],"category_scores_gemma":[0.003812942,0.0001140903,0.0003998082,0.0007110105,0.0001093673,0.0008421543,0.0001017967,0.001923273,0.00002110315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007415811,"about_ca_system_score_gemma":0.004757128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005794792,"about_ca_topic_score_gemma":0.002133775,"domain_scores_codex":[0.9947094,0.0003271553,0.0007684415,0.0003860844,0.001620606,0.002188273],"domain_scores_gemma":[0.9966916,0.001000385,0.0006294526,0.0005315565,0.0009300284,0.0002169054],"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":[0.0002092895,0.00004093243,0.0007107781,5.056748e-7,0.0002036877,0.000001592431,0.0006455707,0.4505774,0.00004030029,0.04515127,0.005610981,0.4968077],"study_design_scores_gemma":[0.0003086881,0.00004022888,0.00001491558,0.00000198618,0.00005172401,0.00004641245,0.002280742,0.5019427,0.000004279589,0.4939694,0.001249364,0.00008956757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08648226,0.00904398,0.8987645,0.003850579,0.0003498145,0.0001516368,0.00001048915,0.00002497543,0.001321779],"genre_scores_gemma":[0.9840812,0.004194857,0.005005361,0.0001297165,0.0003010127,0.00001012419,0.000003590904,0.00002297166,0.006251163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8975989,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0603061295836417,"score_gpt":0.3703655743293625,"score_spread":0.3100594447457208,"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."}}