diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 13:35:13 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 13:35:13 -0500 |
| commit | 37cf78b7f696c9eedc0745ebdaa656bff0ab2f81 (patch) | |
| tree | 37bef77b388614e404703dba305f232bed5423bb /README.md | |
| parent | 0db651ac83608ea8f5b94950a391da22f076a142 (diff) | |
protocol: freeze normalized mirror baseline funnel
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 2 |
1 files changed, 2 insertions, 0 deletions
@@ -138,6 +138,8 @@ high finite-sample kernel recovery and that changing forward parameters after observation cannot affect the update. Any scale obtained this way is credited to the weight-mirror baseline until innovation residualization is shown to be load-bearing on top of it. +`MIRROR_BASELINE.md` freezes that comparator's CIFAR-prefix capture, short +accuracy, and conditional full-validation gates. The subsequent V3 mechanism estimates the required A/G matrix statistics directly by perturbing the vectorizer parameter subspace. It remains |
