What does Shared-Input Evidence across Twelve Systems conclude, in numbers, about “Closing the Loop: a Down-Weighting Proposal for Synthesis, and Pre-Registered Tests”?

Answer: Chapter 8 gives a read-only down-weighting proposal for synthesis engines, the distilled Shared-Input Evidence Down-Weighter and a pre-registered test plan; in the demonstration a naive probability of 0.917 is down-weighted to 0.750. Marked boxes separate published evidence, runnable Python calculations (18 programs), classical sources and the author's hypotheses.

Scope of the numbers: Its parameters are illustrative, and all calculations are generated by its programs. Marked boxes separate published evidence, runnable Python calculations (18 programs), classical sources and the author's hypotheses.

中文版

Data table

The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.750, 0.917

naive: 12 systems x 0.2 = log-odds 2.40, P 0.917
within-block rho 1.0: total weight 5.00, log-odds 1.000, P 0.731
within-block rho 0.8: total weight 5.48, log-odds 1.097, P 0.750
within-block rho 0.5: total weight 6.60, log-odds 1.320, P 0.789
detail at rho 0.8
  block   size  weight each  contribution
  solar      3        0.385         0.231
  year       3        0.385         0.231
  day        4        0.294         0.235
  number     1        1.000         0.200
  hour       1        1.000         0.200
status: PROPOSAL-ONLY; read-only; synthesis owner decides
Show the full program
# Chapter 8. p81: the read-only down-weighting proposal for a synthesis.
# Systems are grouped into the shared-cycle blocks of p52. Inside a block
# of m systems with within-block correlation rho, each log-odds is scaled
# by 1 / (1 + (m - 1) rho), the exact Gaussian weight of p41; blocks are
# then added as if orthogonal. Every system here reports the same
# illustrative log-odds of +0.2. The output is a proposal for the
# synthesis owner to accept or reject, not a verdict on any person.
import math

BLOCKS = [("solar", ["TROP", "SIDR", "MONB"]),
          ("year", ["ZODI", "NSTAR", "NAYIN"]),
          ("day", ["DAYP", "MANS", "WEEK", "TZOL"]),
          ("number", ["LIFE"]), ("hour", ["HOUR"])]
L = 0.2


def combine(rho):
    parts = []
    for name, members in BLOCKS:
        m = len(members)
        w = 1 / (1 + (m - 1) * rho)
        parts.append((name, m, w, math.fsum(w * L for _ in members)))
    return parts


def prob(lo):
    return 1 / (1 + math.exp(-lo))


naive = math.fsum(L for _, mem in BLOCKS for _ in mem)
print("naive: 12 systems x %.1f = log-odds %.2f, P %.3f"
      % (L, naive, prob(naive)))
for rho in (1.0, 0.8, 0.5):
    parts = combine(rho)
    tot = math.fsum(p[3] for p in parts)
    wt = math.fsum(p[1] * p[2] for p in parts)
    print("within-block rho %.1f: total weight %.2f, log-odds %.3f, P %.3f"
          % (rho, wt, tot, prob(tot)))
print("detail at rho 0.8")
print("  block   size  weight each  contribution")
for name, m, w, c in combine(0.8):
    print("  %-7s %4d %12.3f %13.3f" % (name, m, w, c))
print("status: PROPOSAL-ONLY; read-only; synthesis owner decides")

Single source and citation

Fan, Y. (2026). Down-Weighting Non-Independent Evidence across Twelve Symbolic Systems: Spurious Resonance from a Shared Birth Input and Orthogonal Latent-Variable Synthesis (Version 1.0.0), Chapter 8: Closing the Loop: a Down-Weighting Proposal for Synthesis, and Pre-Registered Tests. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-283 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026283,
  author    = {Fan, Yafu},
  title     = {Down-Weighting Non-Independent Evidence across Twelve Symbolic Systems: Spurious Resonance from a Shared Birth Input and Orthogonal Latent-Variable Synthesis},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book