card: fix ACT asset-shape contradiction (single self-contained graph, norm baked in — not split-export/denoise_step)

README.md

@@ -48,17 +48,14 @@ uses one) to a continuous action chunk (act sampler). Produced by
 | Sampling | act |
 | Quantization / precision | none / float16 |
 | On-disk size | 131 MB |
-| Asset kind | single-graph policy + norm_stats sidecar |
+| Asset kind | single-graph policy (self-contained — normalization baked in) |
 | assetVersion | 2.0 |
 
 
 ## Use it — this needs host code you supply
 
 A policy is **not** a chat model: there is no stock high-level Swift runtime for
-it. The bundle is the split-export shape — an `encode` graph (run once per
-observation) + a `denoise_step` graph (the host drives it `num_steps` times) +
-`norm_stats.json` (un-normalization). **You supply the host loop** (the N-step
-sampler + un-normalization) in Swift. Recommended integration: keep LeRobot's
+it. The bundle is a **single self-contained graph** — you run it **once per observation** and it returns the whole action chunk directly. Normalization is **baked into the traced graph** (`predict_action_chunk` normalizes the inputs and un-normalizes the outputs), so there is **no `norm_stats.json` sidecar and no sampler loop** (unlike the flow-matching Pi0/Diffusion bundles). **You supply the host wiring** in Swift — feed the observation tensors, take the returned action chunk. Recommended integration: keep LeRobot's
 Python `RobotClient` for the servos/cameras/calibration, and run inference
 on-device — see the `io_contract` in the catalog for the exact tensors.