Beyond Plausible Prediction: Safety Sufficiency in Web World Models
The authors report that plausible web world-model predictions often fail “safety sufficiency”: semantically plausible futures do not reliably preserve policy-decisive evidence for Execute/Ask/Block decisions. In a human evaluation of 3,000 predictions from ten frozen open models, 86.1% are judged plausible. They introduce SafeWebWorld and Latent Authorisation Recovery (LAR), showing evidence preservation and aggregate score recoverability can still leave fine-grained authorisation failures.
