analysis: identify hierarchical spatial credit bottleneck

1 files changed, 1 insertions, 0 deletions

diff --git a/REVIEW_SCORECARD.md b/REVIEW_SCORECARD.md
index 59fe99e..60c58d3 100644
--- a/REVIEW_SCORECARD.md
+++ b/REVIEW_SCORECARD.md
@@ -77,6 +77,7 @@ retroactively reopened by success on standard vision benchmarks.
 | 2026-07-22 / Oral-A-v2 V2-1 | Six clean frozen-forward records: structured calibration raises early/all-layer alignment to 0.0072/0.0527 but fails two frozen advancement checks | 5 → 5 | Confirms representable-subspace variance was real, while showing that early-layer causal credit remains below the standard-depth gate; V2-2 and confirmation stay closed |
 | 2026-07-22 / post-failure representation oracle | Current family has a 0.0240 cross-validated early-alignment ceiling on the fixed probe versus 0.0072 learned; unconstrained basis coefficients reach 0.0549 | 5 → 5 | Localizes both a causal-regression gap and an output-error-only capacity gap, but an oracle audit supplies no task-performance evidence |
 | 2026-07-22 / Oral-A-v3 V3-1 | Four clean frozen-forward records: vectorizer-space estimation raises all-layer alignment to 0.0626 but leaves early alignment at 0.0071 and fails three advancement checks | 5 → 5 | Exact lower-variance mechanics do not repair early credit; no full ResNet or confirmation evidence is opened |
+| 2026-07-22 / hierarchical oracle | Held-out gated 3x3 maps from exact child error fields reach 0.9998 early alignment; ordinary activation context remains 0.0321 | 5 → 5 | Strongly localizes the missing information to spatial hierarchical error fields, but exact-gradient oracle inputs provide no evidence that the proposed local learner can obtain them |
 
 Future rows are appended only after an audited frozen stage. A score staying flat is informative:
 engineering, theory exposition, or visualization may make the paper more defensible without