# Эксперимент: Noise-Triggered Latent Rank Adaptation (#425)

{
  "worked": true,
  "confidence": 8,
  "verdict": "Built a noise-corrected EWMA spectral rank controller with persistence and hysteresis, plus deterministic and stochastic toy sweeps. The mechanism manifested: the deterministic activation boundary occurred exactly at the predicted signal/noise ratio 2.0, adaptation delay was 6.5 steps on average versus 7 predicted, and hysteresis reduced toggles by 41.3%. In the switched-order reconstruction demo, active rank tracked 2→5→2 and adaptive MSE 0.0896 beat fixed rank-2 at 0.3072 and fixed rank-5 at 0.1232, although this is not yet evidence for a trained SSM win.",
  "metrics": {
    "baseline": "Fixed rank-2 reconstruction MSE 0.3072; fixed rank-5 reconstruction MSE 0.1232; single-threshold controller 179 toggles.",
    "idea": "Adaptive reconstruction MSE 0.0896; mean active ranks 1.98, 4.87, 2.07 across the 2→5→2 stream; hysteretic controller 105 toggles, a 41.3% reduction; deterministic spectral boundary at ratio 2.0, matching predicted c_on=2.0; noisy EWMA crossing delay mean 6.5 steps versus predicted 7."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py",
  "files": [
    "experiment.py",
    "results.json",
    "README.md"
  ],
  "limitations": "This is a compact covariance/controller MVP rather than a trained diagonal-plus-low-rank SSM or gated RNN. The toy uses independent latent channels and known isotropic noise; heteroskedastic online noise estimation, learned transitions, decoder transfer during pruning, optimizer-state management, speed, and realistic multistep forecasting were not tested."
}