# Эксперимент: Adversarially calibrated neural residualization (#500)

{
  "worked": false,
  "confidence": 10,
  "verdict": "Built the adversarial calibration MVP with weight editing, toy parameter sweeps, and a two-fold neural residualization experiment. The core math predicts no editing when w0=1 because w=1 is feasible with zero objective; every sweep confirmed zero edit, zero moment violation, and no dependence on tolerance, critic scale, or critic dimension. The neural experiment likewise showed identical baseline and calibrated estimates, so the promised effect did not manifest under the formula as written.",
  "metrics": {
    "baseline": "hard_mu: absolute bias 0.2751, RMSE 0.2792; hard_pi: absolute bias 0.2598, RMSE 0.2609",
    "idea": "hard_mu: absolute bias 0.2751, RMSE 0.2792; hard_pi: absolute bias 0.2598, RMSE 0.2609; mean ESS 500 and paired coefficient difference 0 in both regimes"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 -W ignore experiment.py",
  "files": [
    "experiment.py",
    "results.json"
  ],
  "limitations": "Only a small synthetic two-fold experiment with eight seeds per regime was tested. No confidence-interval coverage, GPU implementation, true adversarial critic training, or alternative non-unit initial weights were evaluated; the literal w0=1 objective makes the stated calibration edit vacuous."
}