Jackson Eshbaugh | Searcharxiv

arXiv2025

Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity

Computational models have emerged as powerful tools for multi-scale energy modeling research at the building and urban scale, supporting data-driven analysis across building and urban energy systems. However, these models require large amounts of building parameter data that is often inaccessible, expensive to collect, or subject to privacy constraints. We introduce a modular framework that applies generative Artificial Intelligence (AI) to construct simulation-ready building datasets from publicly available records and imagery. To improve the reliability of this framework, we evaluate both its AI components and its overall result. Our occlusion analysis demonstrates that for our selected images, LLaVA achieves greater visual focus than a GPT-based alternative for building image processing. We also assess plausibility of our results against a national reference dataset, finding that our synthetic data overlaps more than 95% for three of the four selected variables. This work aims to reduce dependence on costly or restricted data sources, lowering barriers to building-scale energy research and Machine Learning (ML)-driven urban energy modeling, thereby providing simulation-ready datasets intended to support downstream applications such as energy modeling, retrofit analysis, and urban-scale simulation under data scarcity.

cs.AI↗

arXiv2025

"Faithful to What?" On the Limits of Fidelity-Based Explanations

In explainable AI, surrogate models are commonly evaluated by their fidelity to a neural network's predictions. Fidelity, however, measures alignment to a learned model rather than alignment to the data-generating signal underlying the task. This work introduces the linearity score $\lambda(f)$, a diagnostic that quantifies the extent to which a regression network's input--output behavior is linearly decodable. $\lambda(f)$ is defined as an $R^2$ measure of surrogate fit to the network. Across synthetic and real-world regression datasets, we find that surrogates can achieve high fidelity to a neural network while failing to recover the predictive gains that distinguish the network from simpler models. In several cases, high-fidelity surrogates underperform even linear baselines trained directly on the data. These results demonstrate that explaining a model's behavior is not equivalent to explaining the task-relevant structure of the data, highlighting a limitation of fidelity-based explanations when used to reason about predictive performance.

cs.LG↗