summaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 13:47:35 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 13:47:35 -0500
commit1e4fbaf8e773509798387d19b806f6daf38f8b5c (patch)
tree43d5fe00aa7e1252e884c35cf3ae5a102799f073 /README.md
parent203e75987d02cdb8c317e3302e1f05c9a4beb0e3 (diff)
baseline: add residual response mirroring
Diffstat (limited to 'README.md')
-rw-r--r--README.md7
1 files changed, 7 insertions, 0 deletions
diff --git a/README.md b/README.md
index bf3ce6a..b49774c 100644
--- a/README.md
+++ b/README.md
@@ -141,6 +141,13 @@ load-bearing on top of it.
`MIRROR_BASELINE.md` freezes that comparator's CIFAR-prefix capture, short
accuracy, and conditional full-validation gates.
+After estimate-then-average WM narrowly failed its short accuracy gate, the
+next substantive inherited control uses residual response mirroring. Q predicts
+the observed child response and learns only from the local prediction error;
+unlike WM, its update is zero for every probe at exact symmetry. The extra
+feedback prediction convolution is charged explicitly, and this rule receives
+no SDIL novelty credit.
+
The subsequent V3 mechanism estimates the required A/G matrix statistics
directly by perturbing the vectorizer parameter subspace. It remains
forward-only and uses two causal loss queries per direction. Its exact and