arXiv subjects

Peter Pirolli

Publications and source records attributed to Peter Pirolli.

5 recordsLinked to original sources

arXiv2026

Zenons Demon and the Denial of Domain-Generality for Transformer-Based Computational Models of Human Behavior

Transformer-based models of human behavior (e.g., the Centaur model by Binz, et al., 2025) posit to be domain general computational models of human behavior. The claim of domain-generality is by virtue of the supposed capability to predict and simulate human behavior across a vast range of cognitive and perceptual domains. Further, it is argued that this degree of performance places such models on a path toward general, unified theories of cognition (Newell, 1990). We contest this characterization. We propose the Domain-Generality Thesis: A computational model is domain-general if and only if it performs well across a structurally distinct set of tasks. While transformer-based models of human behavior achieve impressive statistical breadth, we demonstrate that, by example, they fail this structural criterion, conflating parametric variations of a single task with genuine cognitive diversity. We construct an argument that denies the domain-generality of transformer-based models of human behavior and thus denies the purported status as a start on the path towards general, unified theories of cognition.

q-bio.NC↗

arXiv2023

Masking Behaviors in Epidemiological Networks with Cognitively-plausible Reinforcement Learning

The COVID-19 pandemic highlighted the critical role of human behavior in influencing infectious disease transmission and the need for models capturing this complex dynamic. We present an agent-based model integrating an epidemiological simulation of disease spread with a cognitive architecture driving individual mask-wearing decisions. Agents decide whether to mask based on a utility function weighting factors like peer conformity, personal risk tolerance, and mask-wearing discomfort. By conducting experiments systematically varying behavioral model parameters and social network structures, we demonstrate how adaptive decision-making interacts with network connectivity patterns to impact population-level infection outcomes. The model provides a flexible computational framework for gaining insights into how behavioral interventions like mask mandates may differentially influence disease spread across communities with diverse social structures. Findings highlight the importance of integrating realistic human decision processes in epidemiological models to inform policy decisions during public health crises.

cs.SI↗

arXiv2021

Real-Time Learning from An Expert in Deep Recommendation Systems with Marginal Distance Probability Distribution

Recommendation systems play an important role in today's digital world. They have found applications in various applications such as music platforms, e.g., Spotify, and movie streaming services, e.g., Netflix. Less research effort has been devoted to physical exercise recommendation systems. Sedentary lifestyles have become the major driver of several diseases as well as healthcare costs. In this paper, we develop a recommendation system for daily exercise activities to users based on their history, profile and similar users. The developed recommendation system uses a deep recurrent neural network with user-profile attention and temporal attention mechanisms. Moreover, exercise recommendation systems are significantly different from streaming recommendation systems in that we are not able to collect click feedback from the participants in exercise recommendation systems. Thus, we propose a real-time, expert-in-the-loop active learning procedure. The active learners calculate the uncertainty of the recommender at each time step for each user and ask an expert for a recommendation when the certainty is low. In this paper, we derive the probability distribution function of marginal distance, and use it to determine when to ask experts for feedback. Our experimental results on a mHealth dataset show improved accuracy after incorporating the real-time active learner with the recommendation system.

cs.LG↗

arXiv2020

Physical Exercise Recommendation and Success Prediction Using Interconnected Recurrent Neural Networks

Unhealthy behaviors, e.g., physical inactivity and unhealthful food choice, are the primary healthcare cost drivers in developed countries. Pervasive computational, sensing, and communication technology provided by smartphones and smartwatches have made it possible to support individuals in their everyday lives to develop healthier lifestyles. In this paper, we propose an exercise recommendation system that also predicts individual success rates. The system, consisting of two inter-connected recurrent neural networks (RNNs), uses the history of workouts to recommend the next workout activity for each individual. The system then predicts the probability of successful completion of the predicted activity by the individual. The prediction accuracy of this interconnected-RNN model is assessed on previously published data from a four-week mobile health experiment and is shown to improve upon previous predictions from a computational cognitive model.

cs.LG↗

arXiv2012

Thermodynamic Principles in Social Collaborations

A thermodynamic framework is presented to characterize the evolution of efficiency, order, and quality in social content production systems, and this framework is applied to the analysis of Wikipedia. Contributing editors are characterized by their (creative) energy levels in terms of number of edits. We develop a definition of entropy that can be used to analyze the efficiency of the system as a whole, and relate it to the evolution of power-law distributions and a metric of quality. The concept is applied to the analysis of eight years of Wikipedia editing data and results show that (1) Wikipedia has become more efficient during its evolution and (2) the entropy-based efficiency metric has high correlation with observed readership of Wikipedia pages.

cs.SI↗