results: record failed Oral-A full ResNet gate

1 files changed, 14 insertions, 0 deletions

diff --git a/ORAL_A.md b/ORAL_A.md
index 1a07708..be0b32f 100644
--- a/ORAL_A.md
+++ b/ORAL_A.md
@@ -148,3 +148,17 @@ published multi-seed values are not pooled with this matched panel.
   optimizer branch is added after its corresponding screen closes.
 - A strong standard-network result cannot be described as evidence that the
   natural Harnett causal-role/error-derivative signature emerged.
+
+## Audited outcome (2026-07-22)
+
+- A1 passed the primary schedule at `91.62%` validation accuracy; the recovery
+  branch was not used.
+- A2a selected both vectorizer families. A2b selected channel-gated SDIL at
+  hidden LR `0.03`: `41.98%` versus tuned DFA's `37.16%` and BP's `74.94%`.
+- In A3, BP ended at `91.62%` and DFA ended finite at `33.06%`. SDIL became
+  nonfinite at epoch 90 and ended at `10.00%`; its early-third alignment was
+  nonfinite. It passed the BP and MAC checks but failed the four remaining
+  checks.
+- A3 status is `failed`. A4 was not opened, no confirmation JSON was produced,
+  and test seeds 10--14 remain untouched. No recovery or threshold change is
+  permitted by this protocol.