# RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data Source: [RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data]() Collection index: [llms.txt]() Data updated: 2026-06-30T05:00:05.202Z Authors: Xuan Zhao, Lena Krieger, Zhuo Cao, Arya Bangun, Hanno Scharr, Ira Assent Published: 2026-06-26T10:44:01.000Z ## Abstract Counterfactual explanations (CFs) help understand machine learning models by identifying minimal input changes that would lead to alternative model outcomes. Recent work demonstrates their utility for reconstructing black-box models, enabling third-party auditing of opaque decision systems for fairness and accountability. Still, CF-based reconstruction may suffer from decision boundary shifts, overfitting, and restrictive assumptions requiring online query access to target platforms. We propose REconstruction via Counterfactual-Aware waSserstein opTimization (RECAST) under limited data and restricted access, a behavioral surrogate model based on Wasserstein barycentric prototypes. Our approach addresses decision boundary shifts by incorporating CFs as informative, though less representative, samples for both classes, maintaining high surrogate fidelity in low-sample regimes without requiring online access during reconstruction. To enhance fairness auditing, our method enables systematic group fairness diagnostics. Experiments on real-world datasets and various setups show that RECAST effectively achieves high fidelity and query efficiency, as well as stable results even when the access is limited and noisy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Model Reconstruction on Housing](): Model Reconstruction; Housing; Fidelity: 78.9. - [Model Reconstruction on Adult Income](): Model Reconstruction; Adult Income; Average Fidelity: 91.3. - [Model Reconstruction on COMPAS](): Model Reconstruction; COMPAS; Avg Fidelity: 86.9. - [Model Reconstruction on HELOC](): Model Reconstruction; HELOC; Average Fidelity: 79.8. ## Original sources and implementation [Original paper]() [PDF]()