# Эксперимент: Shared-response expert ranking (#1000)

{
  "worked": true,
  "confidence": 9,
  "verdict": "Built a reproducible shared-response router toy experiment with M-weighted scores, exact margin identity, difference-subspace construction, and one-anchor physical correction. The mechanism manifested: algebraic residuals were below 1.2e-14, M-orthogonal corruption changed pairwise rankings by at most 5.1e-14 even at magnitude 100, and the adversarial ranking flip occurred between 1.0 and 1.25 times the predicted threshold. The shared exact correction selected the true best expert and reduced residual evaluations 9x, although the tiny benchmark measured only about 2.6x wall-time speedup.",
  "metrics": {
    "baseline": "All 9 residual diagnostics: approximately 0.135 ms per loop; 9 residual evaluations; true-best candidate 2.",
    "idea": "One shared correction plus score ranking: approximately 0.052 ms per loop; 1 residual/correction; candidate 2 selected; 9x fewer diagnostic calls and approximately 2.6x measured speedup. Formula error 1.15e-14; orthogonal pairwise invariance error <=5.1e-14; predicted flip alpha 0.02308, observed bracket [1.0,1.25]x prediction."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 shared_response_experiment.py",
  "files": [
    "shared_response_experiment.py",
    "README.md"
  ],
  "limitations": "Only a synthetic diagonal-linear physical residual and fixed random candidate library were tested. No learned neural operators, nonlinear PDEs, approximate Jacobian/preconditioner error, noisy response estimates, GPU timing, soft mixtures, confidence certification, or independent real-data ranking accuracy were evaluated."
}