What does Contract Pitfalls and Asset Sovereignty conclude, in numbers, about “The Empirical Loop: a Weekly Anti-Erosion Ledger and Field Tools and Checker Specifications”?

Answer: The ledger turns the book into four tables: contracts, assets, distribution and partners. The tool uses the same formulas as the book's programs to give every row a band. The checker specification is grouped by the four kits, and each provision carries a threshold, a trigger action and a source. The pre-registered tests give their sample sizes: 55 risky clauses, 26 rehearsals, 21 simulated leaks and 49 ended partnerships in each group.

Scope of the numbers: But machine screening is a recall-first screen: on the book's synthetic labelled set only 0.380 of reworded risky clauses are caught, and the costlier a miss, the more a lawyer must read in full. Parameters are illustrative and all calculations are generated by the book's programs.

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: 21, 26, 49, 55

T1 scanner recall 0.800.92: 55 risky clauses
at 0.15 prevalence367 clauses to label
T2 recovery drill success 0.700.90: 26 drills
T3 planted-leak trace rate 0.750.95: 21 leaks
T4 partner loss, red 0.30 vs green 0.1049 per group
z_a 1.6449 z_b 0.8416
Show the full program
# Chapter 8. p82: sample sizes for the pre-registered tests
# One-sample tests of a proportion (normal approximation, one-sided
# alpha 0.05, power 0.80): n = [z_a sqrt(p0 q0) + z_b sqrt(p1 q1)]^2 /
# (p1 - p0)^2. Two-sample test of proportions per group: n = [z_a
# sqrt(2 pb qb) + z_b sqrt(p1 q1 + p2 q2)]^2 / (p1 - p2)^2. Targets come
# from the book's programs; null values are the claims to beat.
import math
from statistics import NormalDist

ZA = NormalDist().inv_cdf(0.95)
ZB = NormalDist().inv_cdf(0.80)


def one(p0, p1):
    a = ZA * math.sqrt(p0 * (1 - p0))
    b = ZB * math.sqrt(p1 * (1 - p1))
    return math.ceil((a + b) ** 2 / (p1 - p0) ** 2)


def two(p1, p2):
    pb = (p1 + p2) / 2
    a = ZA * math.sqrt(2 * pb * (1 - pb))
    b = ZB * math.sqrt(p1 * (1 - p1) + p2 * (1 - p2))
    return math.ceil((a + b) ** 2 / (p1 - p2) ** 2)


n1 = one(0.80, 0.92)
print("T1 scanner recall 0.80 -> 0.92: {} risky clauses".format(n1))
print("   at 0.15 prevalence: {:,} clauses to label".format(
    math.ceil(n1 / 0.15)))
n2 = one(0.70, 0.90)
print("T2 recovery drill success 0.70 -> 0.90: {} drills".format(n2))
n3 = one(0.75, 0.95)
print("T3 planted-leak trace rate 0.75 -> 0.95: {} leaks".format(n3))
n4 = two(0.30, 0.10)
print("T4 partner loss, red 0.30 vs green 0.10: {} per group".format(n4))
print("")
print("z_a {:.4f}  z_b {:.4f}".format(ZA, ZB))

Single source and citation

Fan, Y. (2026). Human-AI Joint Asset and IP Protection, Automated Contract-Loophole Auditing and Full-Spectrum Anti-Erosion Architecture (Version 1.0.0), Chapter 8: The Empirical Loop: a Weekly Anti-Erosion Ledger and Field Tools and Checker Specifications. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-383 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026383,
  author    = {Fan, Yafu},
  title     = {Human-AI Joint Asset and IP Protection, Automated Contract-Loophole Auditing and Full-Spectrum Anti-Erosion Architecture},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book