What it is

If a representation truly understands movement, it should be able to continue it. Predictive runs is our research direction for short-horizon forecasting: given the last seconds of skeletal motion, roll the model forward two to three seconds and read out likely continuations — runs, overlaps, pressing triggers — as probabilities, not certainties.

This page is labeled Research on purpose. Nothing here is shipped, and forecasting quality is a claim we will make with evaluation results — or not at all.

ExampleShort-horizon rollout: one observed trajectory, a fan of probable continuations. Conceptual illustration.

How it works

The mechanism under investigation is generative rollout: the same foundation model that reconstructs masked movement can, in principle, be sampled forward in time. Today the simulation stack is an evaluation workbench — reconstruction, denoising, counterfactual probing — and forward rollouts are the research frontier built on top of it.

What it would unlock

ParameterValueNotes
Horizon2–3 sShort enough to learn, long enough to matter.
Outputdistribution over continuationsProbabilities, never scripted predictions.
Readinganalyst-facing reviewDecision support in review, not in-game automation.
Gateevaluation results firstShips when forecast quality survives the eval suite.

Status & roadmap

Research

Research. Short-horizon forecasting is a direction, not a feature: it builds on validated reconstruction capability and inherits every caveat of proof-of-concept data scale. Progress will be published through the evaluation docs first.