figures: disclose EP evaluation state initialization

1 files changed, 3 insertions, 1 deletions

diff --git a/experiments/plot_main_figures.py b/experiments/plot_main_figures.py
index 9f719d9..19d3819 100644
--- a/experiments/plot_main_figures.py
+++ b/experiments/plot_main_figures.py
@@ -574,7 +574,9 @@ BP is a nonlocal reference and is excluded from frontier construction. Labels gi
 Within each matched architecture, every method uses the same budget: 25 epochs for d1 and 60 epochs
 for d2. EP retains its published raw-pixel, hard-sigmoid energy dynamics and relaxation
 schedule; SDIL retains its z-scored, tanh feedforward dynamics. Thus architecture, examples, and
-epochs are matched, but preprocessing and state dynamics are intentionally method-native.
+epochs are matched, but preprocessing and state dynamics are intentionally method-native. EP
+training particles persist across presentations as published; test particles are freshly
+zero-initialized and run for the full free-phase schedule at each evaluation.
 
 **Figure 2 | Credit-assignment scaling in deep local-learning networks.** Mean ± sample standard
 deviation across five seeds on the same CIFAR-10 width-64 residual MLP protocol. **a,** Test