Related papers: Calibrating Chevron for Preemption
Most of the knowledge Representation formalisms developed for representing prescriptive norms can be categorized as either suitable for representing either low level or high level norms.We argue that low level norm representations do not…
We extend opinion dynamics on discourse sheaves to incorporate "directional stubbornness": agents may hold fixed positions in specified directions of their opinion stalk while remaining flexible in others. This converts the equilibrium…
Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…
Any scientific attempt to explain consciousness is tasked with reconciling the third person objective perspective of science with our first person subjective experience of the world. A good point of departure is to consider situations in…
Homeowners around the world elevate houses to manage flood risks. Deciding how high to elevate a house poses a nontrivial decision problem. The U.S. Federal Emergency Management Agency (FEMA) recommends elevating existing houses to the Base…
As the most public component of the Supreme Court's decision-making process, oral argument receives an out-sized share of attention in the popular media. Despite its prominence, however, the basic function and operation of oral argument as…
This paper studies delegation in a model of discrete choice. In the delegation problem, an uninformed principal must consult an informed agent to make a decision. Both the agent and principal have preferences over the decided-upon action…
Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that…
Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable. We describe a…
Sensing and Perception (S&P) is a crucial component of an autonomous system (such as a robot), especially when deployed in highly dynamic environments where it is required to react to unexpected situations. This is particularly true in case…
We present a behavioral definition of an agent's perceived implication that uniquely identifies a subjective state-space representing her view of a decision problem, and which may differ from the modeler's. By examining belief updating…
Networks of interdependent industrial assets (clients) are tightly coupled through physical processes and control inputs, raising a key question: how would the output of one client change if another client were operated differently? This is…
In recent years, deep learning researchers have focused on how to find the interpretability behind deep learning models. However, today cognitive competence of human has not completely covered the deep learning model. In other words, there…
There is a curious absence of legal constraints on U.S. government agencies undertaking potentially risky scientific research. Some of these activities may present a risk of killing millions or even destroying the planet. Current law leaves…
The thesis of this essay is that, in heterogeneous agent macroeconomics, the assumption of rational expectations about equilibrium prices is unrealistic and should be replaced. Rational expectations imply that decision makers forecast…
We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a preference-learning problem. A policy gateway maintains a Gaussian-process…
Causal relationships play a pivotal role in research within the field of public administration. Ensuring reliable causal inference requires validating the predictability of these relationships, which is a crucial precondition. However,…
This year, jurisdictions worldwide, including the United States, the European Union, the United Kingdom, and China, are set to enact or revise laws governing frontier AI. Their efforts largely rely on the assumption that increasing model…
Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications.…
Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for…