# Эксперимент: Response-Sufficient Neural Memory (#982)

{
  "worked": true,
  "confidence": 9,
  "verdict": "Built a response-sufficient memory bottleneck and an analytic Gaussian-Poisson event-stream verification. The martingale residual check had 0.06% relative variance error; the estimated response-heterogeneity gap followed the predicted lambda^2 scaling with 0.19% median relative error and the predicted (1-rho^2) scaling with 0.56% median relative error. At rho=0.35, the response-aware coordinate reduced held-out kernel MSE from 0.885 for the nuisance/correlation proxy to approximately 4e-22, demonstrating the intended mechanism. The future observable MSE itself did not improve because this toy includes irreducible Poisson noise and does not train a recurrent predictor.",
  "metrics": {
    "baseline": "Nuisance/correlation proxy: kernel MSE 0.8853 at rho=0.35; estimated gap 6.1684. Future-observable MSE was 6.9250 in the direct response comparison (essentially equal to the baseline because irreducible martingale noise dominates).",
    "idea": "Response-sufficient supervised bottleneck: kernel MSE approximately 4e-22 at rho=0.35; estimated gap 0.0368 versus the nuisance gap 6.1684. Lambda-sweep median relative error to G proportional to lambda^2: 0.00187; rho-sweep median relative error to G proportional to 1-rho^2: 0.00563."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py && /home/maxwelhelp/main/bin/python3 - <<'PY'\nimport numpy as np\nfrom experiment import draw\nfrom response_memory import ResponseSufficientMemory\nx,r,k,y,c=draw(50000,.35,1.0,777)\nfor h in (x,r):\n m=ResponseSufficientMemory(1).fit(h[:,None],k)\n print(m.kernel_mse(h[:,None],k))\nPY",
  "files": [
    "experiment.py",
    "response_memory.py",
    "results.json"
  ],
  "limitations": "The implementation uses an analytically available event-consequence kernel rather than counterfactual rollouts or automatic differentiation. It is a scalar supervised bottleneck demonstration, not a trained GRU/SSM on delayed-copy sequences; no wall-clock, memory-size, or end-to-end long-horizon task win was established. The binned conditional-gap estimator has finite-bin bias, especially near rho=0.99."
}