Papers
arxiv:2609.12441

IMPLY: Physically Anchored Consistency for World-Model Rollouts

Published on Sep 11
Authors:
,

Abstract

A new evaluation method, IMPLY, scores world-model rollouts by whether a single physical object explains them, anchored to calibration evidence, revealing that self-consistency alone cannot distinguish correct from incorrect internalized objects.

A world model asked what happens if an object is pushed at several speeds produces several futures. If the model has the object in mind, those futures agree about it: each implies the same mass and friction. The consistency checks now used to vet world-action models ask whether a model's futures agree with each other, and none of them knows any physics. We show that this is not enough, and what to do instead. IMPLY reads the physics each rollout implies by inverting a simulator and scores a set of rollouts by how well one object explains all of them, anchored to two calibration pushes the model has observed. In a controlled setting, self-consistency gives a perfect score to a model that ignores the object and always predicts a typical push; anchoring exposes it (AUROC 0.70 versus 1.00). On a real model, V-JEPA 2-AC adapted to the scene, the same thing happens. Given its own calibration pushes the model tracks the object (per-object correlation with the truth 0.91); given another object's, it does not (0.05). Self-consistency cannot tell these apart, preferring the right evidence on 52% of objects, chance level, while anchored disagreement prefers it on 73% and correlates 0.92-0.99 with the rollouts' error. Used to choose among candidate rollout sets, it comes within 0.003 of an oracle that sees the truth. A model that has internalised the wrong object is exactly as self-consistent as one that has internalised the right one; consistency has to be anchored to evidence.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.12441 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.12441 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.12441 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.