diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 03:10:57 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 03:10:57 -0500 |
| commit | d39da697bdef292b0a48e4fe1ccc93ed32187e06 (patch) | |
| tree | bf59c7e51554715da4b1b081834795c6672f9a6c /ROADMAP.md | |
| parent | 2b98b4e12fd50e582f1826bce206f0dc0f55157a (diff) | |
results: close failed C1 recovery branch
Diffstat (limited to 'ROADMAP.md')
| -rw-r--r-- | ROADMAP.md | 8 |
1 files changed, 8 insertions, 0 deletions
@@ -76,6 +76,14 @@ toward smaller `rho`. No-traffic harm must remain within 0.5 points. If soma or is eligible, stop without evaluating FashionMNIST test. Otherwise freeze that level for a five-model-seed, 95-run test confirmation under the original C1 per-realization gate. +**FashionMNIST recovery status: failed validation on 2026-07-22; test remains unevaluated.** Soma +traffic passed strongly in both projections. Neither top-down level was eligible: at `rho=0.2`, +projection 1234 gained only `+1.300` points and both residual endpoints were more than 3 points +below no traffic; at `rho=0.5`, both gains were large but both residual endpoints were more than +10 points below no traffic. This closes the predeclared recovery branch. C1 remains failed, and +the supported mechanism claim is narrowed to removal of soma-predictable ordinary traffic rather +than arbitrary contextual apical traffic. + ### C2. SDIL scales when depth is useful Flattened CIFAR is retained as a preservation result, not as evidence that added depth is used. |
