summaryrefslogtreecommitdiff
path: root/NOVELTY.md
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 13:33:33 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 13:33:33 -0500
commit0db651ac83608ea8f5b94950a391da22f076a142 (patch)
treeaae335ea16eb1b2f8981ba1217b2f91cdc2ae9b9 /NOVELTY.md
parentc27e0824a41e6c54dd9079f17c20c306c5f2e9c9 (diff)
baseline: add normalized local response mirroring
Diffstat (limited to 'NOVELTY.md')
-rw-r--r--NOVELTY.md6
1 files changed, 6 insertions, 0 deletions
diff --git a/NOVELTY.md b/NOVELTY.md
index 449aa54..ebb10d2 100644
--- a/NOVELTY.md
+++ b/NOVELTY.md
@@ -65,6 +65,12 @@ not by itself make recursive learned feedback novel. It is treated as a
credit-path engineering component unless the complete innovation model shows a
load-bearing residualization result beyond those mandatory comparators.
+Likewise, the normalized local response-mirror path is explicitly inherited
+from weight mirroring/weight estimation. Even if it recovers BP-level scale,
+that performance belongs to the baseline. A paper-level SDIL gain requires the
+somato-dendritic innovation subtraction to remain necessary on top of the
+mirrored hierarchical path under a frozen mixed-traffic intervention.
+
## Candidate SDIL contribution
The candidate contribution is the combination