What does Machine Prose and Human Cadence conclude, in numbers, about “Burstiness, Autocorrelation and the Share of Short Sentences: Rhythm Lives in Order”?

Answer: The burstiness index was built for the gaps between events; applied to sentence lengths it is merely the coefficient of variation on another scale. Program p23 showed that one set of lengths in three orders leaves the coefficient of variation and B untouched while the autocorrelation moves from 0.703 to -0.292 and the flat pairs from 0.818 to none. Half of the sense of breathing lies in the distribution and half in the order. Program p22 warned that in a draft of ten sentences the sampling noise of these numbers is so large that they carry almost no information; a judgement needs at least twenty sentences, and measures of order need many more.

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: -0.292, 0.703, 0.818, 22

orderCVBr1MASD/meanflat
ascending0.604-0.2470.7030.1840.818
shuffled0.604-0.2470.3550.5750.182
alternating0.604-0.247-0.2920.8840.000
alternating order: [4, 19, 6, 22, 9, 26, 12, 31, 14, 38, 17, 45]
Show the full program
# Chapter 2. p23: the same twelve lengths in three orders.
# CV and B depend only on the multiset of lengths, so they cannot see
# order. Order shows up in r1, in the mean absolute successive
# difference relative to the mean (MASD/mean), and in the share of
# "flat" neighbour pairs whose ratio stays within 1.5. The twelve
# lengths are an illustrative multiset chosen by the author.
import math
import random

LENS = [4, 6, 9, 12, 14, 17, 19, 22, 26, 31, 38, 45]


def measures(xs):
    n = len(xs)
    m = math.fsum(xs) / n
    sd = math.sqrt(math.fsum((x - m) ** 2 for x in xs) / n)
    den = math.fsum((x - m) ** 2 for x in xs)
    r1 = math.fsum((xs[i] - m) * (xs[i + 1] - m)
                   for i in range(n - 1)) / den
    masd = math.fsum(abs(xs[i + 1] - xs[i]) for i in range(n - 1)) / (n - 1)
    flat = len([1 for i in range(n - 1)
                if abs(math.log(xs[i + 1] / xs[i])) < math.log(1.5)])
    return sd / m, (sd - m) / (sd + m), r1, masd / m, flat / (n - 1)


rng = random.Random(39405)
shuffled = LENS[:]
rng.shuffle(shuffled)
lo, hi = LENS[:6], LENS[6:]
alternating = [v for pair in zip(lo, hi) for v in pair]
orders = [("ascending", LENS), ("shuffled", shuffled),
          ("alternating", alternating)]
print("order          CV       B       r1  MASD/mean   flat")
for name, xs in orders:
    cv, b, r1, ms, fl = measures(xs)
    print("{:<11} {:>6.3f} {:>7.3f} {:>8.3f} {:>10.3f} {:>6.3f}".format(
        name, cv, b, r1, ms, fl))
print("alternating order:", alternating)

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 2: Burstiness, Autocorrelation and the Share of Short Sentences: Rhythm Lives in Order. 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