关于「溯源的边界:文本长度、开放集与语体混淆」,《扶乩意动与乩文溯源》给出的定量结论是什么?
结论:第六章检验短文本与开放集:300 个字、阈值 0.45 时,名单外作者被错扣的比例降到 0.043,名单内仍有 0.940 被正确指认。
数据口径:立项蓝图把三层都写成既定事实;核对原始文献后,本书把后两层修正为有模型、待检验的假说,并说明法拉第 1853 年检验的是转桌而不是乩笔。 书中参数为示意,乩文语料全部为自拟合成示范;全部计算由书中程序生成。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.043, 0.45, 0.940, 300
| texts of 300 syllables | ||
| threshold t | in-list named right | D wrongly named |
| 0.00 | 1.000 | 1.000 |
| 0.40 | 0.997 | 0.413 |
| 0.45 | 0.940 | 0.043 |
| 0.50 | 0.777 | 0.000 |
| texts of 100 syllables | ||
| threshold t | in-list named right | D wrongly named |
| 0.00 | 0.987 | 1.000 |
| 0.40 | 0.410 | 0.003 |
| 0.45 | 0.203 | 0.000 |
| 0.50 | 0.037 | 0.000 |
查看完整验算程序
# Chapter 6. p62: the open-set trap and an abstention threshold
# Same seeded generator as p51. A closed-set method always names one of
# the candidates, even when the real writer, here a fourth medium D who
# is not on the list, wrote the text. Rule: name the best candidate
# only if its bigram cosine is at least t; otherwise abstain. For each t
# we report, on 300 fresh seance texts by in-list writers (A, B, C) and
# 300 by D, the share correctly named and the share of D's texts that
# are wrongly pinned on someone. Synthetic data only.
# 模型:开放集溯源与弃权阈值;语料全部为自拟合成示范。
import bisect
import math
import random
from collections import Counter
SYL = ("zhi hu zhe ye yi er qi suo wei yu ze nai ru ruo gu fu bu wu"
" you ren xin tian di shan shui yue ri feng yun hua men jia lu"
" chun qiu he jiang shi wen ming").split()
OWN = {"A": "cha jiu qin shu", "B": "mai dou can sang",
"C": "chuan hai qiao zhou"}
DEITY = "shen xian fo sheng dan jing tan luan".split()
SEEDS = {"A": 11, "B": 22, "C": 33}
def profile(name):
# an author's habits: a locally shuffled Zipf order of the shared
# syllables and one favourite successor for each syllable
rng = random.Random(SEEDS[name])
order = list(range(len(SYL)))
for _ in range(30):
i = rng.randrange(len(SYL) - 1)
j = min(len(SYL) - 1, i + 1 + rng.randrange(6))
order[i], order[j] = order[j], order[i]
weight = [0] * len(SYL)
for rank, idx in enumerate(order):
weight[idx] = 600 // (rank + 2)
habit = [rng.randrange(len(SYL)) for _ in SYL]
return weight, habit
def write(name, length, deity, rng):
# deity register: a shared ritual vocabulary at rate 0.2 and a
# doubled taste for the four sentence particles
weight, habit = profile(name)
if deity:
weight = [w * 2 if i < 4 else w for i, w in enumerate(weight)]
topic, rate = DEITY, 0.20
else:
topic, rate = OWN[name].split(), 0.10
cum, tot = [], 0
for w in weight:
tot += w
cum.append(tot)
out, prev = [], None
for _ in range(length):
u = rng.random()
if u < rate:
tok = topic[rng.randrange(len(topic))]
prev = None
elif prev is not None and u < rate + 0.12:
prev = habit[prev]
tok = SYL[prev]
else:
prev = bisect.bisect_right(cum, rng.randrange(tot))
tok = SYL[prev]
out.append(tok)
return out
def corpus(rng):
own = {m: [write(m, 400, False, rng) for _ in range(5)]
for m in "ABC"}
truth = "AABBBC"
revealed = [write(m, 300, True, rng) for m in truth]
return own, revealed, truth
SEEDS["D"] = 44
OWN["D"] = "ma che jie qiang"
def bigrams(tokens):
return Counter(zip(tokens, tokens[1:]))
def cosine(a, b):
keys = sorted(set(a) & set(b))
dot = math.fsum(a[k] * b[k] for k in keys)
na = math.sqrt(math.fsum(v * v for v in a.values()))
nb = math.sqrt(math.fsum(v * v for v in b.values()))
return dot / (na * nb) if na and nb else 0.0
def best(text, big):
b = bigrams(text)
sims = [cosine(b, big[m]) for m in "ABC"]
top = max(sims)
return "ABC"[sims.index(top)], top
if __name__ == "__main__":
rng = random.Random(20261112)
own, _, _ = corpus(rng)
big = {m: bigrams([t for e in own[m] for t in e]) for m in "ABC"}
for length in (300, 100):
inset = []
for _ in range(300):
who = "ABC"[rng.randrange(3)]
inset.append((who, best(write(who, length, True, rng), big)))
outset = [best(write("D", length, True, rng), big)
for _ in range(300)]
print("texts of {} syllables".format(length))
print(" threshold t in-list named right D wrongly named")
for t in (0.0, 0.40, 0.45, 0.50):
good = len([1 for w, (n, s) in inset if s >= t and n == w])
bad = len([1 for n, s in outset if s >= t])
print(" {:11.2f} {:19.3f} {:15.3f}".format(
t, good / 300, bad / 300))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《扶乩意动效应微肌电、乩笔轨迹随机游走与乩文语言模型溯源母典》第 6 章「溯源的边界:文本长度、开放集与语体混淆」(版本 1.0.0). 5D Library. DOI 待发布
DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-226 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026226,
author = {Fan, Yafu},
title = {Ideomotor Micro-Movements in Spirit Writing, Random-Walk Stylus Trajectories and Stylometric Attribution of Revealed Texts},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}