Model card: neutral eval-set wording

README.md

@@ -57,8 +57,6 @@ MIT distribution):
    arm/leg sides are reassigned geometrically. A provenance ledger of every
    pack is kept with the training corpus.
 
-Mixamo characters are used **for evaluation only** — never trained on.
-
 Weights released under **CC-BY-4.0**; please credit *QtMeshEditor*.
 
 ## Evaluation (v2)
@@ -69,11 +67,11 @@ scatter):
 
 | eval set | v1.1.0 | v2.0.0 |
 |---|---|---|
-| Mixamo rig-truth, 3 characters (out-of-distribution, eval-only) | 31.5% | **94.7%** |
+| out-of-distribution rigged test characters (held out of training entirely) | 31.5% | **94.7%** |
 | held-out CC0 rigs (suit, dress, sheep, velociraptor) | — | 97.0% |
 | held-out synthetic bodies | — | 95.6% |
 
-Per-part recall on the Mixamo set (v2): head 0.99, torso 0.80, left arm 0.99,
+Per-part recall on the out-of-distribution set (v2): head 0.99, torso 0.80, left arm 0.99,
 right arm 1.00, left leg 0.87, right leg 0.96. Torso is lowest by construction:
 the ground truth comes from skinning weights, whose shoulder/hip boundaries
 don't coincide exactly with any geometric boundary.