summaryrefslogtreecommitdiff
path: root/ROADMAP.md
diff options
context:
space:
mode:
Diffstat (limited to 'ROADMAP.md')
-rw-r--r--ROADMAP.md8
1 files changed, 8 insertions, 0 deletions
diff --git a/ROADMAP.md b/ROADMAP.md
index ee89703..b4fa72b 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -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.