同一世界，不同知识：孤立审计何时误判世界模型修复
Same World, Different Knowledge: When Isolated Audits Misjudge World-Model Repairs
- University of Florida（佛罗里达大学）
- University of South Carolina（南卡罗来纳大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对世界模型修复，提出信息接口审计，区分保真度与可用性差距，并通过四旋翼实验证明修复选择取决于部署时的信息路径。
AI中文摘要：
在孤立输入故障下被青睐的修复方案，当部署模块共享故障信息时可能表现更差。我们提出了一种用于世界模型的信息接口审计，区分保真度差距（精确输入变为估计值）与可用性差距（输入缺失）。固定权重干预测量预测误差、输入依赖性以及成对闭环收益，包括由重建引入的依赖性。在模拟四旋翼模型预测控制中，耦合的、反号的10%质量/推力标定误差将物理锚定模型的成功率从69%降至8%；不确定性训练恢复了65%。风场重建恢复了控制收益，但继承了标定依赖性。对于正的标定偏移，仅重建损坏有利于不确定性训练的重建，而共享损坏则有利于基线。加速度诊断揭示了重建偏差与标称模型误差之间的补偿，这在扰动观测器中也被观察到。因此，修复选择取决于部署中使用的信息路径。
英文摘要：
A repair favored under an isolated input fault can be inferior when deployed modules share the faulty information. We introduce an information-interface audit for world models, distinguishing fidelity gaps, where exact inputs become estimates, from availability gaps, where inputs are missing. Fixed-weight interventions measure prediction error, input dependence, and paired closed-loop benefit, including dependencies introduced by reconstruction. In simulated quadrotor model predictive control, coupled, opposite-sign 10% mass/thrust calibration errors reduce a physics-anchored model's success from 69% to 8%; uncertainty training restores 65%. Wind reconstruction recovers control benefit but inherits calibration dependence. For a positive calibration offset, reconstruction-only corruption favors uncertainty-trained reconstruction, whereas shared corruption favors the baseline. Acceleration diagnostics reveal compensation between reconstruction bias and nominal-model error, also observed with a disturbance observer. Repair selection therefore depends on the information paths used in deployment.
