OccStress: Stress-Testing the 4D Occupancy Forecasting Chain

Occupancy world models use historical occupancy states to forecast future 3D scenes, but their robustness under corrupted temporal inputs remains poorly understood. Existing evaluations primarily emphasize clean forecasting accuracy and provide limited evidence about how errors enter, persist, and propagate through the occupancy perception-forecasting chain. This paper introduces OccStress, a robustness stress-testing benchmark for the occupancy forecasting chain. OccStress contains 61 corruption categories and 80k+ anchors. OccStress covers both 3D occupancy perception and 4D occupancy forecasting through two complementary tracks. This design separates realistic pipeline errors from the intrinsic sensitivity of 4D forecasting models to corrupted occupancy states. OccStress further defines temporal injection protocols to test whether errors in the current state, recent history, or earlier history affect future forecasts differently. OccStress provides aggregate metrics to evaluating robustness along occupancy forecasting chain. Experiments on OccStress reveal that current occupancy models are substantially affected by both upstream prediction errors and direct state corruptions, and that clean performance alone is an insufficient indicator of temporal robustness. Dataset: https://hf.co/datasets/OccStress/OccStress. Code: https://anonymous.4open.science/r/OccStress.