6 papers
Successive Schur-Riesz Analysis for Approximation
Matthew Francis Dixon
Many approximation methods enlarge a trial space by adjoining function blocks generated by different operators. Exact redundancy and strong cross-level interaction can make coeffic…
Identification and Honest Recovery from Semantic Observation Kernels: Operator Error, Coarsening, and Stability
Matthew Francis Dixon
Probabilistic text generators, such as large language models, assign probabilities to phrases, but consequential decisions require posterior uncertainty over meaningful states. The…
Calibrating Semantic Uncertainty from Observable Language-Model Probabilities
Matthew F. Dixon
As generative artificial intelligence enters scientific and professional work, its uncertainty must be defined on the states that matter for inference and decision-making. Language…
Adaptive AI Delegation under Uncertainty: A Bayesian Governance Policy for Sequential Decision Authority
Matthew Francis Dixon
Organizations increasingly use large language models and agentic AI systems to generate probabilistic assessments and candidate actions in high-consequence settings. This creates a…
Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation
Matthew Francis Dixon
Agentic artificial intelligence systems introduce a new class of model risk. Unlike traditional predictive models, autonomous agents continuously acquire information, form beliefs…
Belief at Risk: Quantifying Agentic AI Model Risk with LLM-Inferred Bayesian State Filters
Matthew Francis Dixon
Agentic AI systems create model risk because uncertain beliefs are coupled to autonomous actions. This paper develops a mathematical framework for quantifying agentic AI risk by re…