What does Disaster Recovery and Threshold Shares conclude, in numbers, about “Closing the Loop: Threshold Drills, the Risk Calculator and a Pre-Registered Test”?

Answer: Chapter 8 gives the drill procedure, the Threshold Share Risk Calculator and a pre-registered test of 30 drills with at least 28 successes. Marked boxes separate published evidence, runnable Python calculations (19 programs), classical sources and the author's hypotheses.

Scope of the numbers: Chapter 6 computes self-rescue after one share goes missing: losing the fastest holder is like raising the threshold by one, and the illustrative rescue window is 263 hours. Marked boxes separate published evidence, runnable Python calculations (19 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: 28, 30

drills N30, pass if at least 28 succeed
false pass if true rate 0.800.0442
power if true rate 0.950.8122
4 drills a year x1 households -> 8 year(s)
4 drills a year x5 households -> 2 year(s)
2 drills a year x 10 households2 year(s)
the claim is refuted if 3 or more of the 30 drills fail
Show the full program
# Chapter 8. p82: how many drills before the book's claim can fail?
# Pre-registered test. Outcome per drill: k shares gathered and the toy
# value rebuilt within 72 h (yes / no). Book's prediction for a 3-of-5
# layout: success rate at least 0.95. Refutation threshold: a true rate
# of 0.80 or lower. Exact one-sided binomial design: smallest number of
# drills N and pass mark c with P(X >= c | 0.80) <= 0.05 (a weak set-up
# rarely looks good) and P(X >= c | 0.95) >= 0.80 (a good one passes).
import math

P0, P1, ALPHA, POWER = 0.80, 0.95, 0.05, 0.80


def upper(n, p, c):
    terms = [math.comb(n, j) * p ** j * (1 - p) ** (n - j)
             for j in range(c, n + 1)]
    return math.fsum(terms)


design = None
for n in range(5, 200):
    for c in range(n + 1):
        a = upper(n, P0, c)
        if a <= ALPHA:
            b = upper(n, P1, c)
            if b >= POWER:
                design = (n, c, a, b)
            break
    if design:
        break
n, c, a, b = design
print("drills N = %d, pass if at least %d succeed" % (n, c))
print("false pass if true rate 0.80: %.4f" % a)
print("power if true rate 0.95:      %.4f" % b)
for per_year, homes in ((4, 1), (4, 5), (2, 10)):
    years = math.ceil(n / (per_year * homes))
    print("%d drills a year x %2d households -> %d year(s)"
          % (per_year, homes, years))
fails = n - c
print("the claim is refuted if %d or more of the %d drills fail"
      % (fails + 1, n))

Single source and citation

Fan, Y. (2026). Disaster Recovery for Digital Assets: Shamir Secret-Sharing Thresholds, Off-Site Incremental Snapshots and Self-Rescue from Single Points of Loss (Version 1.0.0), Chapter 8: Closing the Loop: Threshold Drills, the Risk Calculator and a Pre-Registered Test. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-272 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026272,
  author    = {Fan, Yafu},
  title     = {Disaster Recovery for Digital Assets: Shamir Secret-Sharing Thresholds, Off-Site Incremental Snapshots and Self-Rescue from Single Points of Loss},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book