Model card: piper is a reference example, drop its eval numbers

README.md

@@ -15,7 +15,12 @@ pipeline_tag: robotics
 # openpi_lab — real-robot π₀ checkpoints + the datasets they were trained on
 
 Two robots, each with its trained π₀ weights and the exact LeRobot dataset behind them.
-Everything here has been run on real hardware, not only in replay.
+
+**G2** is the main release — trained, validated on hardware in four stages, and it completes
+its task closed-loop from live camera observations.
+**Piper** is a **reference example**: a second robot with a different arm count, action space
+and control rate, provided so the pipeline can be followed on a contrasting setup. It ships
+the checkpoints and data only; no evaluation results are claimed for it.
 
 ```
 g2/model/        π₀, 30k steps            g2/dataset/     58 ep / 48,332 frames / 10 Hz
@@ -59,7 +64,7 @@ Each server publishes its deployment contract in the connect-time metadata
 > Piper is 30 Hz. Actions are absolute (G2) or delta-from-start (Piper) joint targets;
 > stepping G2's chunk at 30 Hz would execute it 3× too fast.
 
-## Results
+## Results (G2)
 
 **G2** — offline replay against a live server, 120 frames / 12 episodes:
 
@@ -72,15 +77,9 @@ Each server publishes its deployment contract in the connect-time metadata
 Validated on hardware in four stages — dry-run → ground-truth replay → policy-replay on
 dataset observations → live closed loop — and completes the task in the last stage.
 
-**Piper** — replay eval, all 4 tasks GO: pi0 joint MAE 0.74° / cos 0.940; pi0.5 0.44° / cos 0.995.
-Real-robot success rates over 160 rollouts (10 per model × task × condition):
-
-| model | in-dist | OOD-L1 | overall |
-|---|---|---|---|
-| baseline QwenOFT | 55% | 30% | 42.5% |
-| ctxdemo QwenLAP | 80% | 75% | 77.5% |
-| **π₀** | **85%** | **80%** | **82.5%** |
-| π₀.₅ | 80% | 60% | 70% |
+**Piper** is included as a **worked example**, not as a results claim: a second robot with a
+different arm count, action space and control rate, so the pipeline can be compared against
+something other than G2. No success-rate numbers are reported for it here.
 
 ## Things that will bite you