# Stability-calibrated innovation development protocol

## Status and claim boundary

This is a new post-MT-1 development branch, not a reinterpretation or rescue
of the frozen mixed-traffic result. MT-1 remains failed, MT-2/MT-3 remain
untouched, and no result here changes the reviewer score. The sole question is
whether a local one-sided neutral-regression certificate can remove the
multiplicative instability diagnosed in `THEORY.md` before any new validation
endpoint is designed.

The four-to-one traffic intervention, ResNet-20 architecture, seed-0 forward
initialization, 45k training split, augmentation, batch size 128, LR 0.1,
momentum 0.9, decay `1e-4`, and reciprocal KP path remain unchanged. The
predictor is fitted once from the same 64-example instruction-off calibration
prefix by per-cell affine least squares, then frozen throughout task training.
No validation or test example is evaluated.

For fitted slope `p`, use the stability upper margin

```text
p_stable = p + delta (1 + |p|).
```

Thus the measured neutral residual-soma slope is one-sided nonpositive rather
than a point estimate with uncontrolled sign. This adds a small local
anti-Hebbian component when the traffic fit is exact. It does not lower the
traffic ratio or inspect a forward/feedback weight.

## S0: frozen training-prefix stability grid

The already observed diagnostic candidates `delta=0` and
`delta=sqrt(float32 epsilon)` are ineligible: both retain finite task-active
parameters for one epoch but produce enormous loss/parameter growth and
nonfinite BatchNorm running variances. Before evaluating another margin, freeze
the only remaining grid to

```text
delta in {0.001, 0.003, 0.01, 0.03}.
```

Run exactly the first 352 shuffled/augmented task minibatches for every value.
All four records must share one clean source revision. The loader state is
restored after the neutral fit. Each record must report zero validation and
test evaluations.

A candidate is eligible only if all of the following hold:

- all recorded losses, signal diagnostics, parameters, optimizer states, and
  BatchNorm running statistics remain finite for 352 steps;
- maximum task minibatch loss is at most 10 and the final 32-step mean is at
  most 2.5 (clean KP epoch-1 mean is 1.8315);
- the maximum used-innovation/instruction RMS ratio is at most 2;
- maximum absolute forward and reciprocal-feedback weight is at most 10;
- maximum absolute forward and reciprocal momentum is at most 50;
- the closed-form fit uses 64 observations, has maximum positive neutral
  residual-soma slope at most `1e-7`, and every predictor update flag during
  task training is false;
- initial traffic calibration remains within `1e-5` of ratio 4, task loader
  state restoration is exact, and no held-out evaluation occurs.

Select the smallest eligible margin. If no margin is eligible, close this
one-sided predictor branch without extending the grid. A pass only authorizes
writing a separately frozen validation protocol with a new evaluation
boundary; it supplies no accuracy claim and leaves the paper score at 5/10.

## Audited S0 outcome

S0 fails with no eligible margin. `delta=0.001` and `0.003` first make
BatchNorm running variances nonfinite at steps 252 and 301; their maximum
forward/feedback weights reach `8.16e16` and `1.48e17`. `delta=0.01` and
`0.03` keep every tensor finite for 352 steps but have maximum minibatch losses
of `1.40e5` and `4.97e6`, maximum used/instruction RMS ratios of 538.4 and
6.59, and maximum weights of `8.83e6` and `1.19e8`. All four pass the
one-sided slope certificate, frozen-predictor, traffic-calibration, loader, and
zero-held-out-evaluation checks.

The result shows that sign control alone is insufficient: a discrete momentum
mode also has a lower stability boundary, and time-varying deep covariances can
drive an initially negative effective mode beyond it. The grid is closed
without another margin. No validation protocol is opened and the reviewer
score remains 5/10.