baselines: audit native author runs

1 files changed, 4 insertions, 1 deletions

diff --git a/BASELINES.md b/BASELINES.md
index 34e9f58..cfdb3f5 100644
--- a/BASELINES.md
+++ b/BASELINES.md
@@ -57,7 +57,10 @@ model.Q.mode=sym_Y
 The inherited configuration supplies three convolutional layers plus a
 1500-unit fully connected layer, batch size 32, 400 epochs, label smoothing
 0.05, SGD momentum 0.9, weight decay `1e-4`, two warmup epochs and cosine
-decay. Y and Q use learning rate `0.001`. The paper reports
+decay. The resolved author config uses softmax outputs with MSE loss; Y and Q
+use learning rate `0.001`. The current author loop interprets `n_epochs=400`
+as an epoch-0 evaluation followed by 399 optimization epochs, and the audit
+records both counts rather than silently relabelling them. The paper reports
 `17.03 ± 0.21%` top-1 error (`82.97 ± 0.21%` accuracy) for symmetric-plastic
 BurstCCN.