What does Citation Weight in Generative Search conclude, in numbers, about “Paragraph Length and the Point of the Cut: Chunking, Truncation and an Interior Optimum”?
Answer: Chapter 3 covers chunking and truncation: at a cut of 128 words a conclusion placed first is read 4.5000 times as often as one placed last, and paragraph length has an interior optimum of about 60 to 130 words.
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: 128, 4.5000
| share of paragraphs whose conclusion survives a cut at T | |
| T first middle last | |
| 64 | 1.0000 0.1667 0.0556 |
| 128 | 1.0000 0.5000 0.2222 |
| 256 | 1.0000 1.0000 0.5556 |
| 512 | 1.0000 1.0000 1.0000 |
| mean paragraph length 230.0 tokens | |
| at T | 128 conclusion-first keeps 1.0000, last keeps 0.2222 |
| ratio first / last at T | 128: 4.5000 |
Show the full program
# Chapter 3. p32: conclusion first versus conclusion last under a cut.
# A reranker or generator often reads only the first T tokens of each
# retrieved passage. A paragraph of n sentences of 20 tokens each puts
# its conclusion sentence first, in the middle, or last. Paragraph
# lengths run evenly from 3 to 20 sentences (60 to 400 tokens). The
# conclusion counts as read if its last token falls within T.
# Sentence length, cut points and length range are illustrative.
from fractions import Fraction as F
SENT = 20
LENGTHS = range(3, 21)
def end_token(n, where):
if where == "first":
return SENT
if where == "middle":
return (n // 2 + 1) * SENT
return n * SENT
print("share of paragraphs whose conclusion survives a cut at T")
print("%6s %8s %8s %8s" % ("T", "first", "middle", "last"))
rows = {}
for t in (64, 128, 256, 512):
vals = []
for where in ("first", "middle", "last"):
ok = len([n for n in LENGTHS if end_token(n, where) <= t])
vals.append(F(ok, len(LENGTHS)))
rows[t] = vals
print("%6d %8.4f %8.4f %8.4f" % (t, float(vals[0]), float(vals[1]),
float(vals[2])))
mean_len = F(SENT * (3 + 20), 2)
print("mean paragraph length %.1f tokens" % float(mean_len))
r = rows[128]
print("at T = 128 conclusion-first keeps %.4f, last keeps %.4f" % (
float(r[0]), float(r[2])))
print("ratio first / last at T = 128: %.4f" % float(r[0] / r[2]))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 3: Paragraph Length and the Point of the Cut: Chunking, Truncation and an Interior Optimum. 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 4 · The Discount by Citation Position: Cumulated Gain, Position-Adjusted Word Count and the Sag in the Middle
- Chapter 5 · Verifiability: Why Sources Raise the Chance of Citation, and the Trap of Inferring Features from Outside
- 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