arXiv subjects

Christopher Harding

Publications and source records attributed to Christopher Harding.

3 recordsLinked to original sources

arXiv2025

Data-Driven Modeling of U.S. Ideological Dynamics

The dynamics of political opinion are a critical component of modern society with large-scale implications for the evolution of intra- and international political discourse and policy. Here we utilize recent high-resolution survey data to quantitatively capture leading-order psychological and information-environmental patterns. We then inform simulations of a theoretical dynamical framework with several different models for how populations' ideology evolves over time, including a model which reproduces current macro-scale ideological distributions given the empirical micro-scale data gathered. This effort represents an attempt to discover true underlying trends of political reasoning in general audiences, and to extrapolate the long-term implications of those trends as they interact with the political exposure landscape. Accurate modeling of this ecosystem has the potential to predict catastrophic outcomes such as hyperpolarization, and to inform effective intervention strategies aimed at preserving and rebuilding constructive political communication.

physics.soc-ph↗

arXiv2025

Mantis: A Foundation Model for Mechanistic Disease Forecasting

Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate data sets, bespoke training, and expert tuning, all of which can hinder rapid generation of forecasts for new settings. To help address these challenges, we developed Mantis, a foundation model trained entirely on mechanistic simulations, which enables out-of-the-box forecasting across diseases, regions, and outcomes, even in settings with limited historical data. We evaluated Mantis against 78 forecasting models across sixteen diseases with diverse modes of transmission, assessing both point forecast accuracy (mean absolute error) and probabilistic performance (weighted interval score and coverage). Despite using no real-world data during training, Mantis achieved lower mean absolute error than all models in the CDC's COVID-19 Forecast Hub when backtested on early pandemic forecasts which it had not previously seen. Across all other diseases tested, Mantis consistently ranked in the top two models across evaluation metrics. Mantis further generalized to diseases with transmission mechanisms not represented in its training data, demonstrating that it can capture fundamental contagion dynamics rather than memorizing disease-specific patterns. These capabilities illustrate that purely simulation-based foundation models such as Mantis can provide a practical foundation for disease forecasting: general-purpose, accurate, and deployable where traditional models struggle.

cs.AI↗

arXiv2025

Simulation as Supervision: Mechanistic Pretraining for Scientific Discovery

Scientific modeling faces a tradeoff between the interpretability of mechanistic theory and the predictive power of machine learning. While existing hybrid approaches have made progress by incorporating domain knowledge into machine learning methods as functional constraints, they can be limited by a reliance on precise mathematical specifications. When the underlying equations are partially unknown or misspecified, enforcing rigid constraints can introduce bias and hinder a model's ability to learn from data. We introduce Simulation-Grounded Neural Networks (SGNNs), a framework that incorporates scientific theory by using mechanistic simulations as training data for neural networks. By pretraining on diverse synthetic corpora that span multiple model structures and realistic observational noise, SGNNs internalize the underlying dynamics of a system as a structural prior. We evaluated SGNNs across multiple disciplines, including epidemiology, ecology, social science, and chemistry. In forecasting tasks, SGNNs outperformed both standard data-driven baselines and physics-constrained hybrid models. They nearly tripled the forecasting skill of the average CDC models in COVID-19 mortality forecasts and accurately forecasted high-dimensional ecological systems. SGNNs demonstrated robustness to model misspecification, performing well even when trained on data with incorrect assumptions. Our framework also introduces back-to-simulation attribution, a method for mechanistic interpretability that explains real-world dynamics by identifying their most similar counterparts within the simulated corpus. By unifying these techniques into a single framework, we demonstrate that diverse mechanistic simulations can serve as effective training data for robust scientific inference.

cs.LG↗