What does Citation Weight in Generative Search conclude, in numbers, about “Verifiability: Why Sources Raise the Chance of Citation, and the Trap of Inferring Features from Outside”?
Answer: Chapter 5 treats verifiability and shows by simulation how fragile it is to infer feature weights from outside: leaving out length overstates the weight on statistics by 0.3252.
Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs. It is not individual business advice.
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: 0.3252
| simulated paragraphs 4000, cited 957 | |||
| feature | true | fit (full) | fit (no len) |
| const | -2.00 | -1.983+-0.153 | -2.088 |
| stat | +0.60 | +0.670+-0.167 | +0.995 |
| source | +0.80 | +0.665+-0.154 | +0.642 |
| quote | +0.40 | +0.405+-0.162 | +0.364 |
| stuffing | -0.30 | -0.240+-0.078 | -0.236 |
| length | +0.50 | +0.412+-0.086 | - |
| stat weight inflated by 0.3252 when length is left out |
Show the full program
# Chapter 5. p52: inferring feature weights from outside is fragile.
# "Reverse reading" here means only this: log which public paragraphs
# an engine cites, then fit a logistic model to their visible
# features. We simulate 4000 paragraphs from a known model (weights
# are illustrative), where statistics appear more often in longer
# paragraphs, and fit it twice by Newton's method: with length as a
# control, and without. Without the control the statistics weight
# absorbs part of the length effect. Seeded, so the run is exact.
import math
import random
rng = random.Random(20261113)
TRUE = [-2.0, 0.6, 0.8, 0.4, -0.3, 0.5]
NAMES = ["const", "stat", "source", "quote", "stuffing", "length"]
N = 4000
def sig(z):
return 1 / (1 + math.exp(-z))
def dot(a, b):
return math.fsum(x * y for x, y in zip(a, b))
rows, ys = [], []
for _ in range(N):
ln = rng.gauss(0, 1)
stat = 1.0 if rng.random() < sig(-0.2 + 1.0 * ln) else 0.0
src = 1.0 if rng.random() < 0.4 else 0.0
quo = 1.0 if rng.random() < 0.3 else 0.0
stf = rng.gauss(0, 1)
x = [1.0, stat, src, quo, stf, ln]
rows.append(x)
ys.append(1.0 if rng.random() < sig(dot(TRUE, x)) else 0.0)
def solve(a, b):
n = len(b)
m = [row[:] + [b[i]] for i, row in enumerate(a)]
for c in range(n):
piv = max(range(c, n), key=lambda r: abs(m[r][c]))
m[c], m[piv] = m[piv], m[c]
for r in range(n):
if r != c:
f = m[r][c] / m[c][c]
m[r] = [u - f * v for u, v in zip(m[r], m[c])]
return [m[i][n] / m[i][i] for i in range(n)]
def fit(cols):
xs = [[x[j] for j in cols] for x in rows]
beta = [0.0] * len(cols)
for _ in range(10):
p = [sig(dot(beta, x)) for x in xs]
g = [math.fsum((y - q) * x[j] for x, y, q in zip(xs, ys, p))
for j in range(len(cols))]
h = [[math.fsum(q * (1 - q) * x[j] * x[k]
for x, q in zip(xs, p))
for k in range(len(cols))] for j in range(len(cols))]
step = solve(h, g)
beta = [b + s for b, s in zip(beta, step)]
se = []
for j in range(len(cols)):
e = [1.0 if k == j else 0.0 for k in range(len(cols))]
se.append(math.sqrt(solve(h, e)[j]))
return dict(zip(cols, beta)), dict(zip(cols, se))
full, se_full = fit([0, 1, 2, 3, 4, 5])
omit, se_omit = fit([0, 1, 2, 3, 4])
print("simulated paragraphs %d, cited %d" % (N, int(math.fsum(ys))))
print("%-9s %7s %13s %13s" % ("feature", "true", "fit (full)",
"fit (no len)"))
for j, name in enumerate(NAMES):
om = "%+.3f" % omit[j] if j in omit else "-"
print("%-9s %+7.2f %+7.3f+-%.3f %13s" % (
name, TRUE[j], full[j], 1.96 * se_full[j], om))
print("stat weight inflated by %.4f when length is left out" % (
omit[1] - full[1]))Single source and citation
Fan, Y. (2026). The Geometry of Citation Weight in Generative Search: Retrieval and Reranking Features and the Paragraph Topology of Highly Cited Bilingual Answer Pages (Version 1.0.0), Chapter 5: Verifiability: Why Sources Raise the Chance of Citation, and the Trap of Inferring Features from Outside. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-260 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026260,
author = {Fan, Yafu},
title = {The Geometry of Citation Weight in Generative Search: Retrieval and Reranking Features and the Paragraph Topology of Highly Cited Bilingual Answer Pages},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Measuring Visibility: Why Keyword Stuffing Fails and Why Sources, Figures and Quotations Help
- Chapter 2 · The Geometry of Hybrid Scoring: BM25 Saturation, Cosine Direction and Rank Fusion
- Chapter 3 · Paragraph Length and the Point of the Cut: Chunking, Truncation and an Interior Optimum
- Chapter 4 · The Discount by Citation Position: Cumulated Gain, Position-Adjusted Word Count and the Sag in the Middle
- Chapter 6 · The Paragraph Topology of a Bilingual Direct-Answer Page: Self-Contained Paragraphs, One Set of Numbers on Four Surfaces, and Compliant Structured Data
- Chapter 7 · Classical Sources East and West: the Three Gauges of the Mozi and Garfield's Citation Index
- Chapter 8 · Closing the Loop: an A/B Test of Answer-Paragraph Templates, the Citability Scorer and a Pre-Registered Test