# Эксперимент: Moment-Tuple Propagation for Compressed Neural Inference (#48)

{
  "worked": false,
  "confidence": 9,
  "verdict": "Built experiment.py with five-tuple affine propagation, second-order tanh activation propagation, numerical moment checks, and a seeded MLP compression experiment. Affine identities were exact and the Taylor formulas were accurate in a small-variance local regime, but they failed badly for the broader test distribution. Tuple inference was about 4.6x faster than 32-sample Monte Carlo, yet nominal-90% interval coverage was only 75.7% versus 89.1% for Monte Carlo, so the promised uncertainty quality was not observed.",
  "metrics": {
    "baseline": "RMSE to clean model output 0.10151; 0.000329 ms/sample",
    "idea": "RMSE to clean output 0.10131; 75.7% nominal-90% coverage; 0.002252 ms/sample; 0.01814 RMSE versus MC mean"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py",
  "files": [
    "experiment.py"
  ],
  "limitations": "Only a synthetic two-feature, one-hidden-layer MLP and uniform scalar quantization were tested. The implementation uses diagonal or independent feature statistics, does not calibrate compression metadata from real scientific fields, does not test CUDA, and does not measure metadata memory against the claimed 1% target."
}