# Эксперимент: Exact-Jacobian Flow Controller (#964)

{
  "worked": true,
  "confidence": 9,
  "verdict": "Built a conditional alternating-mask RealNVP-style flow with analytic inverse, clamped scales, exact log-determinant, density, and autodiff score. The mechanism checks confirmed linear log-volume scaling with gamma and layer count, reconstruction error near floating-point precision, and an exact autodiff Jacobian logdet match. The flow also outperformed the diagonal Gaussian MLP on held-out NLL and score RMSE in both tested dimensions.",
  "metrics": {
    "baseline": "Diagonal conditional Gaussian MLP: d=2 NLL 4.466, score RMSE 2.819; d=8 NLL 17.779, score RMSE 2.918.",
    "idea": "Exact-Jacobian flow: d=2 NLL 1.536, score RMSE 1.245; d=8 NLL 4.149, score RMSE 1.299. Math sweep predictions and observations matched exactly for gamma 0, 0.25, 0.5, 1.0, and 1.5; nonlinear Jacobian logdet was 2.018253 versus analytic 2.018253."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py",
  "files": [
    "run_experiment.py",
    "results.json",
    "final_run.txt"
  ],
  "limitations": "The baseline was a diagonal Gaussian MLP rather than a full standard non-invertible flow, and parameter/FLOP matching was only approximate. The experiment used synthetic 2-D/8-D mixtures and one fixed seed; long controller rollouts, multiple tasks, calibration, and large-scale diffusion or world-model integration were not tested."
}