# Эксперимент: Critical-Tail Multiscale Mixer (#1292)

{
  "worked": true,
  "confidence": 7,
  "verdict": "Built a dyadic critical-tail mixer and numerical verification scripts. The discrete tail ratio to 1/log(R+2) approached 1.000 from 0.979 at R=8 to 0.99993 at R=1024, confirming the claimed slow tail decay; dyadic kernel approximation had lower L1 error than a radius-8 local kernel at every tested length. In the learned denoising experiment, validation MSE was 1.0341 versus 1.0389 at L=64 and 1.0162 versus 1.0278 at L=256 for dyadic versus local, with about 18% higher runtime at L=256, indicating a small long-context signal rather than a definitive accuracy win.",
  "metrics": {
    "baseline": "Radius-8 local mixer: val MSE 1.03890 (L=64), 1.02779 (L=256); kernel L1 error 0.46367, 0.48266, 0.49304, 0.49955 at L=64,256,1024,4096; runtime 12.06s at L=256.",
    "idea": "Dyadic tail mixer: val MSE 1.03412 (L=64), 1.01624 (L=256); kernel L1 error 0.25475, 0.25870, 0.25955, 0.25950 at L=64,256,1024,4096; runtime 14.27s at L=256. Tail ratio discrete/(1/log(R+2)) was 0.97896 at R=8 and 0.99993 at R=1024."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py && /home/maxwelhelp/main/bin/python3 verify_and_compare.py",
  "files": [
    "run_experiment.py",
    "verify_and_compare.py"
  ],
  "limitations": "The experiment is a one-dimensional scalar denoising task, not Transformer-scale copy, retrieval, or Long Range Arena. It uses a learned scalar residual rather than the full projected LN/Wv/Wo implementation, has only one seed and short training, and does not benchmark peak memory or compare against attention/linear attention. The dyadic bands use uniform averages, so the approximation is intentionally coarse."
}