summaryrefslogtreecommitdiff
path: root/BASELINES.md
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 13:22:24 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 13:22:24 -0500
commitc24a6a575bce15e7d7da541ecb752c65b5e68e47 (patch)
tree8166e8c7eebf2785cd811e4fbbc1578b185262bc /BASELINES.md
parent225459f7ddfcd3c8d89f0515a0d766bf2a15c848 (diff)
results: close fixed hierarchical FA short gate
Diffstat (limited to 'BASELINES.md')
-rw-r--r--BASELINES.md3
1 files changed, 2 insertions, 1 deletions
diff --git a/BASELINES.md b/BASELINES.md
index 9800d16..6b76d09 100644
--- a/BASELINES.md
+++ b/BASELINES.md
@@ -20,7 +20,8 @@ The audited implementations and completed results are in `RESULTS.md`:
adjoints, and local ReLU/BatchNorm Jacobians; it never copies or reads a
downstream forward convolution and is the mandatory baseline for any learned
hierarchical extension. Its frozen validation-only screen is specified in
- `HFA_BASELINE.md`;
+ `HFA_BASELINE.md`; the selected short endpoint is 43.52% versus matched DFA's
+ 37.16%, but its 50% full-run gate failed;
- direct node perturbation uses a causal target on every hidden update and no
learned vectorizer;
- the no-traffic, `P=0` SDIL backbone is learned direct feedback by node