What does Compliant Rewriting of Absolute Terms conclude, in numbers, about “Closing the Loop: a Compliant-Rewrite Library for the Persuasive-Copy Checker, and a Non-Inferiority Test”?

Answer: Chapter 8 gives the weekly procedure linking a compliant-rewrite library to the persuasive-copy checker, the distilled Compliant Rewriting Automaton, and a pre-registered non-inferiority test: at a relative margin of 0.10 and power of 0.80 each arm needs 39,981 sessions. Marked boxes separate published evidence, runnable Python calculations (18 programs), classical sources and the author's hypotheses.

Scope of the numbers: Its lexicons, copy, facts and parameters are illustrative; all calculations are generated by its programs; it is not individual legal advice and supplies no way of slipping past platform review. 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: 0.10, 0.80, 39981

base conversion 0.030, one-sided alpha 0.05, 4000 sessions a day
margin m  power   n per arm   days   (true rewrite effect 0)
  0.05    0.80      159923     80
  0.05    0.90      221519    111
  0.10    0.80       39981     20
  0.10    0.90       55380     28
  0.15    0.80       17770      9
  0.15    0.90       24614     13
if the rewrite truly loses 0.03 of conversion, margin 0.10:
  n per arm 80406, days 41
decision rule: claim non-inferiority only if the lower one-sided
95 % bound of cB - cA * (1 - m) is above 0; report it either way
Show the full program
# Chapter 8. p82: sample size for a pre-registered non-inferiority test.
# Model: arm A shows the original line, arm B the compliant rewrite.
# H0: c_B <= c_A * (1 - m), H1: c_B > c_A * (1 - m), m = relative margin.
# Normal approximation, one-sided level alpha = 0.05, equal arms:
#   n per arm = (z_{1-alpha} + z_{1-beta})^2 * (vA + vB) / gap^2,
# vA = cA (1 - cA), vB = cB (1 - cB), gap = cB - cA (1 - m), assuming
# the true conversions are equal (cB = cA). Base conversion and daily
# traffic are illustrative. Traffic pooled over a library of listings.
import math
from statistics import NormalDist

Z = NormalDist().inv_cdf
CA = 0.030
DAILY = 4000            # sessions a day across the pooled listings


def n_per_arm(m, power, cb=CA, alpha=0.05):
    gap = cb - CA * (1.0 - m)
    var = CA * (1 - CA) + cb * (1 - cb)
    return math.ceil((Z(1 - alpha) + Z(power)) ** 2 * var / gap ** 2)


print("base conversion %.3f, one-sided alpha 0.05, %d sessions a day"
      % (CA, DAILY))
print("margin m  power   n per arm   days   (true rewrite effect 0)")
for m in [0.05, 0.10, 0.15]:
    for pw in [0.80, 0.90]:
        n = n_per_arm(m, pw)
        print("  %.2f    %.2f  %10d  %5d" % (m, pw, n,
                                            math.ceil(2 * n / DAILY)))
print()
print("if the rewrite truly loses 0.03 of conversion, margin 0.10:")
n = n_per_arm(0.10, 0.80, cb=CA * 0.97)
print("  n per arm %d, days %d" % (n, math.ceil(2 * n / DAILY)))
print("decision rule: claim non-inferiority only if the lower one-sided")
print("95 % bound of cB - cA * (1 - m) is above 0; report it either way")

Single source and citation

Fan, Y. (2026). Compliant Rewriting for Platform-Sensitive Terms: Absolute-Term Automata under the Advertising Law, Meaning-Preserving Rewrites and Conversion Elasticity (Version 1.0.0), Chapter 8: Closing the Loop: a Compliant-Rewrite Library for the Persuasive-Copy Checker, and a Non-Inferiority Test. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-274 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026274,
  author    = {Fan, Yafu},
  title     = {Compliant Rewriting for Platform-Sensitive Terms: Absolute-Term Automata under the Advertising Law, Meaning-Preserving Rewrites and Conversion Elasticity},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book