Qualify development-sheet benchmark

README.md

@@ -22,7 +22,7 @@ model-index:
       split: full
     metrics:
     - type: accuracy
-      name: Clip accuracy
+      name: Provisional development-sheet clip accuracy
       value: 0.9778
 ---
 
@@ -31,11 +31,17 @@ model-index:
 A 1.5M-parameter MobileNetV3-small classifier for hand/gripper visibility in
 robot-training footage. 96px inputs, sized for microcontroller-class deployment.
 
+The published 97.8% result is from a 45-clip, in-domain development sheet that
+was repeatedly consulted during development and has not yet passed the declared
+independent two-grader gate. It is reproducible development evidence, not a
+frozen external benchmark.
+
 ## Benchmark
 
-97.8% clip accuracy on [referee-lab/hands-visible](https://github.com/publu/referee-lab)
-(45-clip public benchmark, robot + wildlife domains) — matching gemma3:27b at
-1/18,000th the parameters.
+97.8% clip accuracy on
+[referee-lab/hands-visible](https://github.com/publu/referee-lab) (45-clip
+provisional development sheet, robot + wildlife domains) — matching gemma3:27b
+on that sheet at 1/18,000th the parameters.
 
 | Model | Params | Accuracy |
 |---|---|---|