What does The Bit Budget of Tieban Shenshu conclude, in numbers, about “Practice and Refutation: A Bit Budget for Intake, Red Lines for Scripts, and a Pre-Registered Test”?

Answer: Chapter 8 gives a pre-registered blind test, needing 65 clients if the true hit rate is 0.10, and distils the results into a script skeleton and red lines for service-desk intake. 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; all calculations are generated by its programs; it analyses structure and probability, makes no reading of any individual, and is not legal or financial advice. Chapter 5 shows that a verse carries at most 0.5307 bits of expected information and that at an illustrative scale 19.01 people are born each minute.

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: 0.10, 65

testnreject if hits >=alphapower
pair, chance vs 0.0523480.00590.9024
pair, chance vs 0.106540.00660.9004
father, chance vs 0.20109170.00880.9009
father, chance vs 0.303780.01000.9053
Show the full program
# Chapter 8. p81: Sample sizes for a pre-registered committed-cell test.
# The reader receives only the double-hour, commits in writing to one
# cell, and the cell's check verse is scored against facts sealed
# before the session. Chance hit rates come from p42: 0.01143 for the
# father-mother pair, 1/12 for the father's animal alone. We find the
# smallest n with a critical count c such that P(X >= c | chance)
# <= 0.01 and P(X >= c | claimed rate) >= 0.90, by exact binomials.
import math


def tail(n, c, p):
    # P(X >= c) for X ~ Binomial(n, p)
    return math.fsum(math.comb(n, k) * p ** k * (1 - p) ** (n - k)
                     for k in range(c, n + 1))


def design(p0, p1, alpha=0.01, power=0.90):
    n = 5
    while True:
        c = 0
        while tail(n, c, p0) > alpha:
            c += 1
        if tail(n, c, p1) >= power:
            return n, c, tail(n, c, p0), tail(n, c, p1)
        n += 1


cases = [("pair, chance vs 0.05", 0.01143, 0.05),
         ("pair, chance vs 0.10", 0.01143, 0.10),
         ("father, chance vs 0.20", 1 / 12, 0.20),
         ("father, chance vs 0.30", 1 / 12, 0.30)]
print("  test                       n   reject if hits >=  alpha   power")
for name, p0, p1 in cases:
    n, c, a, pw = design(p0, p1)
    print("  {:<24}{:>4}   {:>16}  {:.4f}  {:.4f}".format(
        name, n, c, a, pw))

Single source and citation

Fan, Y. (2026). Tieban Shenshu Ke-Fen Decision Trees, Affine Coding of the Verse Bank and Entropy Lower Bounds on Elicitation (Version 1.0.0), Chapter 8: Practice and Refutation: A Bit Budget for Intake, Red Lines for Scripts, and a Pre-Registered Test. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-157 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026157,
  author    = {Fan, Yafu},
  title     = {Tieban Shenshu Ke-Fen Decision Trees, Affine Coding of the Verse Bank and Entropy Lower Bounds on Elicitation},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book