arXiv subjects

Carson Dudley

Publications and source records attributed to Carson Dudley.

8 recordsLinked to original sources

arXiv2026

Reservoir: A Large-Scale Simulated Dataset for Training and Evaluating Epidemiological Models

Large-scale, standardized datasets have driven many advances in AI-based scientific modeling, from protein structure prediction to natural language processing. Infectious disease epidemiology is increasingly adopting AI methods for forecasting, surveillance, and outbreak analytics, but the time-series data available to train them remains orders of magnitude smaller than the corpora behind the advances seen in other fields. Because the scope of real-world epidemiological data cannot practically reach the scale needed to train truly large-scale AI methods, simulated data provides a possible alternative. Here we introduce Reservoir, a large open simulator and dataset of realistic epidemic simulations in which every trajectory carries complete ground-truth labels, including quantities that cannot be measured directly in a real outbreak, such as true infection counts, time-varying reproduction numbers, and counterfactual intervention effects. Reservoir is generated by a stochastic simulator with realistic noise and reporting artifacts, together with interventions with configurable timing, compliance, and age-dependent efficacy. The current release contains 500,000 outbreak trajectories spanning one billion simulated days across diverse pathogen characteristics, population structures, and intervention regimes. Reservoir enables counterfactual experiments, surveillance-design studies, and training of epidemic models at a scale real-world datasets cannot provide.

q-bio.PE↗

arXiv2026

Prediction Markets Underperform Simple Baselines For Infectious Disease Forecasting

Prediction markets (e.g., Polymarket, Kalshi) allow participants to bet on future events, producing real-time forecasts based on collective judgment. In domains such as elections and finance, markets have been effective at aggregating information, often rivaling or outperforming expert forecasters or polls. Whether this performance extends to infectious disease dynamics is unclear. Participants are self-selected and typically lack epidemiological expertise. However, markets can respond in real time to emerging news and unstructured signals in ways that standard forecasting pipelines cannot. Also, substantial financial stakes encourage participants to make an effort to be accurate. We evaluate Polymarket forecasts during 2025 and 2026 for two settings: weekly cumulative influenza hospitalizations in the US, which have an established expert-curated forecasting ensemble (CDC FluSight), and monthly measles cases, which do not. Across both settings, prediction markets fail to outperform standard benchmarks. For influenza, markets are competitive with low-performing individual FluSight models but are dominated by the FluSight ensemble: even when we combine market forecasts with the ensemble, the best combination puts zero weight on the markets. For measles, markets are outperformed by simple statistical baselines. We diagnose two sources of market inefficiency: placement of probability mass on impossible outcomes (e.g., decreasing values in cumulative forecasts) and low trading volume. These results suggest that current prediction markets are not reliable forecasters of infectious disease dynamics on their own or useful as complementary features for existing forecasting systems.

stat.AP↗

arXiv2026

Latent Chain-of-Thought Improves Structured-Data Transformers

Chain-of-thought and more broadly test-time compute are known to augment the expressive capabilities of language models and have led to major innovations in reasoning. Motivated by this success, this paper explores latent chain-of-thought as well as the impact of depth and looping for time-series and tabular data. We propose a recurrent scheme in which a structured-data transformer, after an initial forward pass, compresses its query-position hidden states into feedback tokens that are appended to the input and processed again, allowing multiple rounds of latent computation before prediction. We compare CoT models against a same-depth no-CoT baseline, a deeper baseline matched to the CoT model in effective depth, and a looped transformer with weight-tied recurrence but no additional chain-of-thought tokens. Across 36 datasets in time-series forecasting and tabular prediction, latent chain-of-thought improves over the baseline on 7/9 time-series datasets (+12.63\% average gain) and 23/27 tabular datasets (+3.25\% average gain), with CoT models performing best on average in both settings. We also show that the benefit of CoT extends to pretrained foundation models: applying latent CoT to nanoTabPFN, a small open-source tabular foundation model, improves its performance above the much larger TabPFN-v2 on TabArena. Together, these results demonstrate that chain-of-thought is a useful axis for scaling test-time compute for structured data.

cs.LG↗

arXiv2026

In-Context Learning Under Regime Change

Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models must detect the change, discard or downweight obsolete evidence, and adapt to new dynamics on the fly. Transformer-based foundation models increasingly rely on in-context learning for time series forecasting, tabular prediction, and continuous control. As these models are deployed in non-stationary environments, understanding their ability to detect and adapt to regime shifts is important. We formalize this as an in-context change-point detection problem and formally establish the existence of transformer models that solve this problem. Our construction demonstrates that model complexity, in layers and parameters, depends on the level of information available about the change-point location, from no knowledge to knowing exact timing. We validate our results with experiments on synthetic linear regression and linear dynamical systems, where trained transformers match the performance of optimal baselines across information levels. We also show that encoding and incorporating changepoint knowledge indeed improves the real-world performance of a pretrained foundation models on infectious disease forecasting and on financial volatility forecasting around Federal Open Market Committee (FOMC) announcements without retraining, demonstrating practical applicability to real-world regime changes.

cs.LG↗

arXiv2025

Not All Accuracy Is Equal: Prioritizing Independence in Infectious Disease Forecasting

Ensemble forecasts have become a cornerstone of large-scale disease response, underpinning decision making at agencies such as the US Centers for Disease Control and Prevention (CDC). Their growing use reflects the goal of combining multiple models to improve accuracy and stability versus relying on any single model. However, while ensembles regularly demonstrate stability against individual model failures, improved accuracy is not guaranteed. During the COVID-19 pandemic, the CDC's multi-model ensemble outperformed the best single model by only 1\%, and CDC flu ensembles have often ranked below individual models. Prior work has established that ensemble performance depends critically on diversity: when models make independent errors, combining them yields substantial gains. In practice, however, this diversity is often lacking. Here, we propose that this is due in part to how models are developed and selected: both modelers and ensemble builders optimize for stand-alone accuracy rather than ensemble contribution, and most epidemic forecasts are built from a small set of approaches trained on the same surveillance data. The result is highly correlated errors, limiting the benefit of ensembling. This suggests that in developing models and ensembles, we should prioritize models that contribute complementary information rather than replicating existing approaches. We present a toy example illustrating the theoretical cost of correlated errors, analyze correlations among COVID-19 forecasting models, and propose improvements to model fitting and ensemble construction that foster genuine diversity. Ensembles built with this principle in mind produce forecasts that are more robust and more valuable for epidemic preparedness and response.

stat.AP↗

arXiv2025

Learning From Simulators: A Theory of Simulation-Grounded Learning

Simulation-Grounded Neural Networks (SGNNs) are predictive models trained entirely on synthetic data from mechanistic simulations. They have achieved state-of-the-art performance in domains where real-world labels are limited or unobserved, but lack a formal underpinning. We place SGNNs in a unified statistical framework. Under standard loss functions, they can be interpreted as amortized Bayesian predictors trained under a simulator-induced prior. Empirical risk minimization then yields convergence to the Bayes-optimal predictor under the synthetic distribution. We employ classical results on distribution shift to characterize how performance degrades when the simulator diverges from reality. Beyond these consequences, we develop SGNN-specific results: (i) conditions under which unobserved scientific parameters are learnable via simulation, and (ii) a back-to-simulation attribution method that provides mechanistic explanations of predictions by linking them to the simulations the model deems similar, with guarantees of posterior consistency. We provide numerical experiments to validate theoretical predictions. SGNNs recover latent parameters, remain robust under mismatch, and outperform classical tools: in a model selection task, SGNNs achieve half the error of AIC in distinguishing mechanistic dynamics. These results establish SGNNs as a principled and practical framework for scientific prediction in data-limited regimes.

cs.LG↗

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↗