results: record failed Oral-A full ResNet gate

1 files changed, 18 insertions, 12 deletions

diff --git a/PAPER_PLAN.md b/PAPER_PLAN.md
index a401909..1c958ff 100644
--- a/PAPER_PLAN.md
+++ b/PAPER_PLAN.md
@@ -43,10 +43,11 @@ as a limitation rather than a title claim.
 5. Report the frozen depth panel: SDIL changes by only
    `-0.214 +/- 0.349` points over 12x hidden depth while DFA alignment falls to
    `0.047`; qualify that flattened CIFAR is depth-flat.
-6. Insert the native-baseline and standard-ResNet result only after their
-   strict imports/gates complete. End with the supported scope: innovation is
-   useful for soma-predictable traffic, while learned feedback amortization
-   remains the useful-depth bottleneck.
+6. Report the failed standard-ResNet A3 gate as a limitation: short-run SDIL
+   beat tuned DFA, but the full recipe became nonfinite and did not open A4.
+   End with the supported scope: innovation is useful for soma-predictable
+   traffic, while learned feedback amortization and long-horizon stability
+   remain the useful-depth bottlenecks.
 
 The abstract should not mention the failed desired-velocity hypothesis unless
 the paper explicitly positions that falsification as a contribution. It must
@@ -66,10 +67,11 @@ not imply that no-traffic scaling establishes the necessity of residualization.
    preservation, alignment, query/MAC/memory cost, and direct-versus-amortized
    causal feedback.
 4. **Scientific negatives.** Broad top-down traffic, useful-depth learned
-   vectorization, and the Harnett desired-velocity signature fail their frozen
-   gates, defining the method's actual boundary.
-5. **Standard scale, conditional.** Add only if Oral-A passes its validation
-   and untouched confirmation gates.
+   vectorization, the Harnett desired-velocity signature, and full standard
+   ResNet stability fail their frozen gates, defining the method's actual
+   boundary.
+5. **Standard scale.** Do not claim it: A3 failed and the A4 test panel stayed
+   sealed.
 
 ## Figure order in the manuscript
 
@@ -81,9 +83,9 @@ numbering.
 2. **Accuracy/cost:** current `figure1_pareto`, augmented by the completed
    native-author table in the text or supplement. Do not place unmatched
    architectures on one purported equal-compute frontier.
-3. **Depth scaling:** current `figure2_scaling`. If Oral-A A4 passes, add or
-   replace with the ResNet20/32/56 accuracy, alignment-retention, and local-cost
-   panel; retain the MLP result as controlled diagnosis.
+3. **Depth scaling:** current `figure2_scaling`. Retain the MLP result as a
+   controlled depth-preservation diagnosis; report the failed ResNet-20 A3
+   trajectory in the limitations or supplement, not as a scaling figure.
 4. **Mechanism/cost anatomy:** query-budget retention, direct-NP diagnosis,
    predictor timescale, and failure boundaries. This can be a main figure if
    space permits or a dense supplementary figure.
@@ -151,7 +153,7 @@ numbering.
 |:--|:--|:--|
 | “This is Lansdell synthetic feedback renamed.” | `NOVELTY.md`; no-traffic method explicitly attributed; raw/matched/innovation panel isolates the new operation | Novelty remains narrow and needs clear writing |
 | “The residual only clips an oversized signal.” | Per-example norm-matched raw control; positive scaling preserves cosine; Figure mechanism panel | Artificial predictable traffic is still a controlled construction |
-| “Depth does not help this task.” | Claim says preservation; C2 reports the learned-vectorizer failure; Oral-A targets standard useful scale | Fatal to a broad scaling claim unless Oral-A passes |
+| “Depth does not help this task.” | Claim says preservation; C2 reports the learned-vectorizer failure; Oral-A A3 is retained as a failed standard-scale test | Fatal to a broad scaling claim; the paper must remain mechanism-focused |
 | “Local methods hide enormous extra work.” | Logical queries, MACs, peak memory, wall time, C3 confirmation, EP/native protocols | Hardware implementations are not all equally optimized |
 | “Weak baselines define the win.” | BP/FA/DFA/direct NP/FF/PEPITA/EP plus native BurstCCN and Dual Prop | Native reproductions are one seed and method-native, not equal compute |
 | “Harnett already proves the biological story.” | Oral-B preregistration and complete negative result | Biological contribution is limited without new data or a new passed prediction |
@@ -174,3 +176,7 @@ innovation is load-bearing under identifiable mixed traffic and the inherited
 causal-feedback backbone preserves depth on the controlled task, but standard
 useful scaling remains unresolved. The correct response is a narrower title,
 claim, and score—not another post-hoc ResNet tuning branch.
+
+This is the realized branch: A3 SDIL became nonfinite at epoch 90 and ended at
+chance. A4 remained untouched. The working title therefore stays
+mechanism-focused, and the standard-ResNet result is a disclosed limitation.