diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 13:47:35 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 13:47:35 -0500 |
| commit | 1e4fbaf8e773509798387d19b806f6daf38f8b5c (patch) | |
| tree | 43d5fe00aa7e1252e884c35cf3ae5a102799f073 /README.md | |
| parent | 203e75987d02cdb8c317e3302e1f05c9a4beb0e3 (diff) | |
baseline: add residual response mirroring
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 7 |
1 files changed, 7 insertions, 0 deletions
@@ -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 |
