{"id":"W7106809557","doi":"10.48448/07v9-4z77","title":"Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Benchmark (surveying); Simple (philosophy); Risk assessment; Occupational safety and health; System safety","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01715668,0.001370828,0.0007788679,0.002095027,0.001322119,0.003714679,0.002274232,0.002007482,0.004519258],"category_scores_gemma":[0.1018962,0.0005563935,0.001193846,0.001085675,0.001946654,0.00711797,0.004257994,0.002490378,0.002617686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001845836,"about_ca_system_score_gemma":0.003768207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008556947,"about_ca_topic_score_gemma":0.0115539,"domain_scores_codex":[0.9758123,0.01222268,0.002349483,0.00235955,0.006435236,0.00082079],"domain_scores_gemma":[0.9226175,0.04100119,0.004079966,0.02121369,0.009517428,0.001570201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004597695,0.002097494,0.08037915,0.004259588,0.001225075,0.0008605404,0.005275757,0.09393305,0.03225294,0.05796663,0.1289475,0.5882046],"study_design_scores_gemma":[0.0005773567,0.003146621,0.01983373,0.00139977,0.0005522884,0.001183369,0.003493391,0.6124589,0.0926654,0.1173227,0.1468903,0.0004762427],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6181244,0.008190667,0.2401537,0.007450444,0.00127717,0.0009214198,0.01507744,0.05545673,0.05334795],"genre_scores_gemma":[0.8435233,0.001061201,0.1207796,0.001522482,0.0001176249,0.0004100015,0.02265367,0.004121681,0.005810415],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01715668,"threshold_uncertainty_score":0.09073424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07635180137532895,"score_gpt":0.3835188232736459,"score_spread":0.307167021898317,"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."}}