Same World, Different Knowledge: When Isolated Audits Misjudge World-Model Repairs

2026-09-17

AI Summary

研究通过引入信息接口审计方法，解决了在模块共享错误信息时孤立审计可能误判世界模型修复的问题。

Abstract

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.

Problem

• world model
• repair
• information interface
• fidelity gap
• availability gap

Innovation

• information-interface audit
• fidelity gaps
• availability gaps
• fixed-weight interventions
• uncertainty training