results: audit Dual Prop state-bias screen

1 files changed, 5 insertions, 1 deletions

diff --git a/paper/ONE_PAGE.html b/paper/ONE_PAGE.html
index 777e38f..d39017e 100644
--- a/paper/ONE_PAGE.html
+++ b/paper/ONE_PAGE.html
@@ -71,6 +71,10 @@
       control reach 10.38% and 10.31% accuracy. SDIL reaches <b>97.35%</b>. Across five seeds, its
       paired gain over the magnitude-matched control is <b>87.038 ± 0.607 points</b>. Matching signal
       size does not explain the result; subtraction changes the direction used for learning.</p>
+      <p>In a new author-code Dual Prop screen, activity-dependent bias makes raw learning nonfinite
+      in epoch 1 at all three strengths. Innovation remains finite and reaches 71.10%, 70.18%, and
+      68.96%, within 0.90 points of exact bias subtraction. The core comparison passes, but the
+      complete development gate fails its clean/common endpoint controls.</p>
     </div>
     <div>
       <h2>Accuracy versus cost</h2>
@@ -83,7 +87,7 @@
 
   <h2>What would make the paper stronger</h2>
   <ul>
-    <li>Show the same failure and recovery inside strong contrastive learners; the frozen Dual Prop bias screen is running now.</li>
+    <li>Repeat the Dual Prop recovery across seeds after freezing a corrected same-path identity control.</li>
     <li>Finish the matched CNN, ResNet, and Transformer comparison; report accuracy, runtime, memory, and update cost together.</li>
     <li>Test bias that drifts or is only partly predictable. Random noise is a negative control because this subtraction cannot remove it.</li>
   </ul>