What does Machine Prose and Human Cadence conclude, in numbers, about “Classical Sources: Han Yu on Breath and Words, Liu Xie on Fours and Sixes, Aristotle on Rhythm, Longinus on Harmony”?

Answer: Han Yu's length of words, Liu Xie's fours and sixes, Aristotle's neither metre nor formlessness, and Longinus's harmony on a par with thought all say one thing: rhythm is part of the content. Program p71 showed that Liu Xie's sentence on construction is so even that its coefficient of variation is only 0.096, while Han Yu's sentence is a sharp contrast of two characters and twelve. Program p72 showed that the high coefficient of variation of a famous text can come from one long sentence, and that its sampling band is too wide to serve as a standard. The classics give a direction, not numbers; the numbers must come from the ledger.

Scope of the numbers: All examples are synthetic text written by the author or public-domain text, parameters are illustrative, and every calculation is generated by the book's programs. Marked boxes separate published evidence, runnable Python calculations (21 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: 0.096

Liu Xieclauses [6, 5, 6, 6, 6, 7]mean 6.00CV 0.096contrast 1.4
Han Yuclauses [2, 12]mean 7.00CV 0.714contrast 6.0
Liu Xie clauses within 3 to 7 hanzi: 6 of 6
Show the full program
# Chapter 7. p71: clause lengths in two classical Chinese sentences.
# Texts as transcribed on zh.wikisource (simplified here): Liu Xie,
# Wenxin Diaolong, "Zhangju"; Han Yu, "Da Li Yi shu" (the Quan Tang wen
# reading, without the particle zhe). One sentence from each, public
# domain. Clauses are split at the full-width comma and semicolon;
# lengths are hanzi counts. The contrast ratio is longest / shortest.
import math
import re

LIU = "若夫笔句无常,而字有条数,四字密而不促,六字格而非缓,或变之以三五,盖应机之权节也。"
HAN = "气盛,则言之短长与声之高下皆宜。"


def clauses(s):
    parts = re.split(r"[,;。]", s)
    return [len(re.findall(r"[一-鿿]", p)) for p in parts if p]


for name, s in (("Liu Xie", LIU), ("Han Yu", HAN)):
    xs = clauses(s)
    m = math.fsum(xs) / len(xs)
    sd = math.sqrt(math.fsum((x - m) ** 2 for x in xs) / len(xs))
    print("{:<8} clauses {}  mean {:.2f}  CV {:.3f}  contrast {:.1f}".format(
        name, xs, m, sd / m, max(xs) / min(xs)))
# Liu Xie's claim read as a band: clause lengths 4 to 6, varied by 3 or
# 5. Share of his own clauses that fall inside 3 to 7 hanzi:
xs = clauses(LIU)
inside = len([x for x in xs if 3 <= x <= 7])
print("Liu Xie clauses within 3 to 7 hanzi: {} of {}".format(inside, len(xs)))

Single source and citation

Fan, Y. (2026). Stripping Statistical Fingerprints of Machine Prose, Sentence-Length Burstiness Reconstruction and Master-Level Stylistic Cadence (Version 1.0.0), Chapter 7: Classical Sources: Han Yu on Breath and Words, Liu Xie on Fours and Sixes, Aristotle on Rhythm, Longinus on Harmony. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-394 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026394,
  author    = {Fan, Yafu},
  title     = {Stripping Statistical Fingerprints of Machine Prose, Sentence-Length Burstiness Reconstruction and Master-Level Stylistic Cadence},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book