What does Anti-Spam Detection and Compliant Bridge Pages conclude, in numbers, about “The Price of Links: Demotion Thresholds, Information Posts and the Binomial Test”?

Answer: Chapter 4 shows that link share and clicks follow a curve that rises and then collapses, and an account that is all links is identified from 3 sampled posts.

Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; it is general business analysis, not personalised business, legal or financial advice, and rules must be checked by a human reviewer before publication. Marked boxes separate published evidence, runnable Python calculations (20 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 only

link share xclicks, x0 known 0.30clicks, x0 unknown
0.00.00.0
0.126.124.2
0.244.436.8
0.335.735.7
0.410.724.2
0.51.99.5
0.60.32.0
0.70.00.3
0.80.00.0
0.90.00.0
1.00.00.0
best share if x0 known: 0.23 (45.7 clicks)
best share if x0 unknown: 0.24 (37.9 clicks)
clicks at x 0.40 if x0 is 0.30: 10.7; at x 0.20: 44.4
Show the full program
# Chapter 4. p41: link share against a demotion threshold.
# Model (illustrative): an account posts N = 14 times a week; a share x
# of posts carry an outbound promotional link. Each post reaches
# R = 1,000 people times two factors: the platform's demotion curve
# m(x) = 1 / (1 + exp((x - x0) / 0.05)) and audience engagement
# e(x) = 1 - 0.5 x (link-heavy feeds are read less). A link post earns
# clicks at rate 0.02 of its reach. Weekly clicks:
#   C(x) = N x R m(x) e(x) 0.02.
# Case A: the threshold x0 = 0.30 is known. Case B: x0 is unknown and
# uniform on 0.10 to 0.50 (41 grid points); we average C over x0.
import math

N, R, CTR = 14, 1000, 0.02


def clicks(x, x0):
    m = 1 / (1 + math.exp((x - x0) / 0.05))
    return N * x * R * m * (1 - 0.5 * x) * CTR


def grid_x0():
    return [0.10 + 0.01 * i for i in range(41)]


def expected(x):
    return math.fsum(clicks(x, z) for z in grid_x0()) / 41


if __name__ == "__main__":
    print("link share x   clicks, x0 known 0.30   clicks, x0 unknown")
    for i in range(0, 11):
        x = i / 10
        print("{:>12.1f} {:>23.1f} {:>20.1f}".format(
            x, clicks(x, 0.30), expected(x)))
    xs = [i / 100 for i in range(101)]
    ka = max(xs, key=lambda x: clicks(x, 0.30))
    kb = max(xs, key=expected)
    print("best share if x0 known: {:.2f} ({:.1f} clicks)".format(
        ka, clicks(ka, 0.30)))
    print("best share if x0 unknown: {:.2f} ({:.1f} clicks)".format(
        kb, expected(kb)))
    print("clicks at x 0.40 if x0 is 0.30: {:.1f}; at x 0.20: {:.1f}"
          .format(clicks(0.40, 0.30), clicks(0.20, 0.30)))

Single source and citation

Fan, Y. (2026). Social-Graph Anti-Spam Detection Bounds, Compliant Affiliate Bridge-Page Funnels and the Kinetics of Recovery after Reach Throttling (Version 1.0.0), Chapter 4: The Price of Links: Demotion Thresholds, Information Posts and the Binomial Test. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-342 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026342,
  author    = {Fan, Yafu},
  title     = {Social-Graph Anti-Spam Detection Bounds, Compliant Affiliate Bridge-Page Funnels and the Kinetics of Recovery after Reach Throttling},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book