docs: integrate dynamic stability branch into paper plan

1 files changed, 39 insertions, 8 deletions

diff --git a/PAPER_PLAN.md b/PAPER_PLAN.md
index 8e85aae..80eacef 100644
--- a/PAPER_PLAN.md
+++ b/PAPER_PLAN.md
@@ -46,10 +46,12 @@ as a limitation rather than a title claim.
 6. Report native BurstCCN and Dual Prop as method-native context, including
    their unmatched protocols and audited walls. 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 full recipe became nonfinite and did not open A4. The later dynamic
+   neutral-projection D2 result may be mentioned as a short seed-0 recovery
+   (`83.58%`) but cannot support a full-scale abstract claim unless D3 and its
+   independent confirmation pass. End with the supported scope: innovation is
+   useful for soma-predictable traffic, while learned feedback amortization and
+   independently confirmed long-horizon stability remain bottlenecks.
 
 The abstract should not mention the failed desired-velocity hypothesis unless
 the paper explicitly positions that falsification as a contribution. It must
@@ -72,8 +74,9 @@ not imply that no-traffic scaling establishes the necessity of residualization.
    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.
+5. **Standard scale.** Do not claim it yet: A3 failed and the dynamic
+   projection branch currently has only one short validation endpoint. A
+   predeclared full D3 result plus independent confirmation is required.
 
 ## Figure order in the manuscript
 
@@ -89,8 +92,10 @@ numbering.
    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.
+   predictor timescale, and failure boundaries. The audited
+   `figureS_dynamic_stability` gives the clearest current sequence—fixed
+   predictor explosion, continually removed neutral coupling, and restored
+   short-run learning—and should move into the main paper if D3 passes.
 5. **Biological signatures:** the complete failed Oral-B screen belongs in the
    supplement/limitations unless the paper foregrounds falsification. Report
    its positive decodability and negative causal-role results together.
@@ -118,6 +123,8 @@ numbering.
 ### 3. Theory and resource accounting
 
 - Conditional projection and task-period absorption.
+- Multiplicative residual coupling, the two-sided momentum/Jury stability
+  window, and fast neutral projection as a local empirical certificate.
 - Hidden alignment versus parameter descent.
 - Simultaneous perturbation bias/variance.
 - Logical loss queries, MACs, memory, and wall time as separate axes.
@@ -159,6 +166,7 @@ numbering.
 | “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 |
+| “The fast controller is just an unreported contrastive phase.” | Paired neutral observation count and elementwise/wall cost are explicit; no task-nudged state, loss query, or reverse pass is used | The instruction-off microphase is a real assumption and weakens the single-phase biological claim |
 | “The gates were selected after results.” | Git-frozen protocols, untouched confirmation seeds, failed branches retained | Early inherited pilots predate the strict boundary and must remain labeled |
 
 ## Result-dependent branch
@@ -220,3 +228,26 @@ predictor-warmup, query, and cost invariants. MT-2 and MT-3 remain untouched.
 The paper therefore retains the mechanism-focused title and 5/10 assessment;
 the controlled standard-ResNet recovery is a disclosed negative result, not an
 active acceptance claim.
+
+## Post-MT-1 operator-stability branch
+
+MT-1 remains failed and its sealed MT-2/MT-3 panels are never reopened. The
+separate post-failure theory identifies the predictor error as the
+multiplicative operator `D W C`; S0 then falsifies fixed sign-only margins.
+`DYNAMIC_INNOVATION.md` defines a new evaluation boundary: a slow neutral
+predictor plus a fast paired instruction-off projection of the remaining
+neutral residual. This is closer to a local apical shunting/homeostatic
+controller than to Dual Prop's two oppositely nudged task states, but the paper
+must disclose the extra microphase rather than call the method single-phase.
+
+D1 passes its training-only stability gate. D2 then reaches `83.58%` at 20
+epochs versus clean KP's `82.66%`, while the failed raw/matched controls remain
+at `10%`; all projection, query, MAC, memory, and evaluation-boundary checks
+pass. This is the first standard-ResNet evidence for load-bearing innovation,
+but it is one short validation run and therefore leaves the score at 5/10.
+
+The predeclared D3 run is the next paper-changing gate. Only a complete
+near-BP 200-epoch pass can move the simulated reviewer score to 6 and authorize
+an independently frozen multi-seed test confirmation. If D3 fails, preserve
+the dynamic short result as a stability diagnosis and do not replace the
+schedule, thresholds, or traffic intervention.