algorithm: calibrate feedback in representable subspace

1 files changed, 5 insertions, 1 deletions

diff --git a/README.md b/README.md
index a690477..d13f8f4 100644
--- a/README.md
+++ b/README.md
@@ -98,7 +98,11 @@ The convolutional infrastructure can be checked independently:
 These checks cover deterministic CIFAR splitting/augmentation, the standard
 CIFAR `6n+2` ResNet topology, exact local convolution and BatchNorm
 eligibilities, the BatchNorm-coupled perturbation objective, predictor fitting,
-translation-shared feedback, and parameter/cost accounting.
+translation-shared feedback, representable-subspace causal calibration, and
+parameter/cost accounting.  The latter is a transparent post-A3 development
+path: it perturbs the channel-gated basis directly and reproduces the expected
+full-field delta rule with far less irrelevant spatial variance.  It does not
+retroactively reopen or relabel the failed frozen Oral-A protocol.
 
 `experiments/finalize_accept.sh` additionally requires strict imports of the
 frozen BurstCCN and Dual Propagation author-code runs. Both records now pass;