{"id":"W7084056929","doi":"10.1109/yac66630.2025.11149732","title":"Uncertainty Propagation in AI-driven Autonomous Systems","year":2025,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Probabilistic logic; Propagation of uncertainty; Modular design; Domain (mathematical analysis); Uncertainty analysis; Series (stratigraphy); Uncertainty quantification; Stability (learning theory)","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":[0.0002983694,0.00008797964,0.0001300274,0.0001913467,0.00006917081,0.0001389403,0.0005622063,0.00005668941,0.000007066254],"category_scores_gemma":[0.00009905535,0.00007820575,0.00002334105,0.0005934649,0.00001980466,0.0003529865,0.0002378236,0.0001975945,0.0000275763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001898739,"about_ca_system_score_gemma":0.0001613029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006040048,"about_ca_topic_score_gemma":0.00007268937,"domain_scores_codex":[0.9990553,0.0001209151,0.0002168268,0.0002898894,0.0001336947,0.0001833471],"domain_scores_gemma":[0.9994581,0.00008188467,0.00004997257,0.0003335301,0.00005203384,0.00002446394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001771728,0.00001186261,0.003287978,0.00001461587,0.000003433758,0.000005425816,0.0001268675,0.6265654,0.00004421742,0.3633461,0.000196752,0.006395619],"study_design_scores_gemma":[0.0002344771,0.00001217541,0.002539654,0.00004117935,0.000001519668,0.000001654321,0.0000372924,0.9933538,0.00004008271,0.001420486,0.002232813,0.00008484463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004009035,0.00002644114,0.973321,0.001980603,0.0006895335,0.000238897,1.379068e-7,0.0002493176,0.01948499],"genre_scores_gemma":[0.9850772,9.1008e-7,0.01216839,0.0003011631,0.00002971073,0.00002564634,0.000001459272,0.000003516509,0.00239203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9810681,"threshold_uncertainty_score":0.3189138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008201894414738653,"score_gpt":0.268832635689608,"score_spread":0.2606307412748693,"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."}}