关于「嫌疑名单:零维短条码、伪装与基础比率」,《社群拓扑体检》给出的定量结论是什么?
结论:第五章把零维短条做成嫌疑名单:检出率 0.996、真实账号误报率 0.0127,但互刷账号占比很低时名单上 0.717 的人是无辜的;伪装使检出率跌到 0.028,L3 的 AUC 仍为 0.900。
数据口径:书中所有社群与成员都是固定种子的合成数据,不使用任何真实社群或个人的数据;全部计算由书中程序生成,参数为示意;本书是非个人化经营建议,「水军识别」只产出供人工复核的嫌疑名单,不自动处罚任何成员。 第二章用并查集求零维条码、用模 2 列约化求一维条码,在两百个合成社群上,点赞总数的 AUC 只有 0.427,一维条码前三长之和 L3 为 0.975;补量社群的真实核心增至 30 人时降到 0.673,此时须靠零维短条。
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: 0.0127, 0.996
| delta | sock recall | precision | relatives | others | per genuine | false rate |
|---|---|---|---|---|---|---|
| 0.10 | 0.769 | 1.000 | 0.000 | 0.0000 | 0.00 | 0.0000 |
| 0.15 | 0.916 | 1.000 | 0.033 | 0.0000 | 0.13 | 0.0043 |
| 0.20 | 0.996 | 1.000 | 0.095 | 0.0000 | 0.38 | 0.0127 |
| 0.25 | 0.999 | 1.000 | 0.312 | 0.0000 | 1.25 | 0.0417 |
| 0.30 | 1.000 | 1.000 | 0.652 | 0.0015 | 2.65 | 0.0883 |
| 0.35 | 1.000 | 0.998 | 0.897 | 0.0142 | 3.96 | 0.1320 |
查看完整验算程序
# Chapter 5. p51: A suspect list from short zero-dimensional bars.
# Rule: join accounts whose Jaccard distance is below delta (the H0 bars
# that die before delta); every group of at least 3 accounts goes on a
# list for human review. Nobody is penalised by the rule. Tested on
# 100 padded communities (12 real + 18 lockstep) and 100 genuine ones
# that contain a family of 4 relatives with near-identical likes
# (26 others + 4 relatives). Synthetic, fixed seed, illustrative.
import random
T, P = 24, 5 # 24 topics on a ring, 5 posts each (illustrative)
N_POSTS = T * P
def member(rng, centre, width, q=0.8, stray=0.03):
# a genuine member likes posts on an arc of topics around centre
s = set()
for t in range(T):
dd = abs(t - centre) % T
dd = min(dd, T - dd)
hit = q if dd <= width / 2.0 else stray
for k in range(P):
if rng.random() < hit:
s.add(t * P + k)
return s
def sock(rng, target, q=0.95, stray=0.01):
# a boosting account likes the operator's target posts in lockstep
s = set()
for p in range(N_POSTS):
if rng.random() < (q if p in target else stray):
s.add(p)
return s
def community(rng, n_real, arc, n_sock):
# n_real genuine members with interest centres on [0, arc) topics,
# plus n_sock boosting accounts aimed at 30 target posts
pts = []
for _ in range(n_real):
pts.append(member(rng, rng.uniform(0, arc), rng.randint(5, 8)))
target = set(rng.sample(range(N_POSTS), 30))
for _ in range(n_sock):
pts.append(sock(rng, target))
return pts
def jaccard(a, b):
u = len(a | b)
return 1.0 - len(a & b) / u if u else 0.0
def barcodes(pts, cap=1.0):
return barcodes_d(len(pts), lambda i, j: jaccard(pts[i], pts[j]), cap)
def barcodes_d(n, dist, cap=1.0):
# Vietoris-Rips filtration (up to triangles) of a distance dist(i, j).
# H0 by union-find; H1 by mod-2 reduction of triangle columns,
# each column stored as a Python integer used as a bitset of edges.
edges = []
for i in range(n):
for j in range(i + 1, n):
d = dist(i, j)
if d <= cap:
edges.append((d, i, j))
edges.sort()
eid = {(i, j): k for k, (d, i, j) in enumerate(edges)}
par = list(range(n))
def find(x):
while par[x] != x:
par[x] = par[par[x]]
x = par[x]
return x
h0, neg = [], set()
for k, (d, i, j) in enumerate(edges):
a, b = find(i), find(j)
if a != b:
par[max(a, b)] = min(a, b)
h0.append((d, i, j))
neg.add(k)
tris = []
for (i, j), e in eid.items():
for k in range(j + 1, n):
f, g = eid.get((i, k)), eid.get((j, k))
if f is not None and g is not None:
tris.append(tuple(sorted((e, f, g), reverse=True)))
tris.sort()
piv, h1 = {}, []
for t in tris:
col = (1 << t[0]) | (1 << t[1]) | (1 << t[2])
while col:
low = col.bit_length() - 1
if low not in piv:
piv[low] = col
break
col ^= piv[low]
if col and edges[t[0]][0] > edges[low][0]:
h1.append((edges[low][0], edges[t[0]][0]))
for k in range(len(edges)):
if k not in neg and k not in piv:
h1.append((edges[k][0], cap)) # still open at the cap
return h0, h1
def family(rng, k=4, keep=0.85):
base = member(rng, rng.uniform(0, 24), rng.randint(5, 8))
out = []
for _ in range(k):
s = set(p for p in sorted(base) if rng.random() < keep)
s |= set(p for p in range(N_POSTS) if rng.random() < 0.01)
out.append(s)
return out
def flagged(pts, delta, m=3):
n = len(pts)
par = list(range(n))
def find(x):
while par[x] != x:
par[x] = par[par[x]]
x = par[x]
return x
for i in range(n):
for j in range(i + 1, n):
if jaccard(pts[i], pts[j]) < delta:
par[find(i)] = find(j)
size = {}
for i in range(n):
r = find(i)
size[r] = size.get(r, 0) + 1
return [i for i in range(n) if size[find(i)] >= m]
rng = random.Random(20261113)
pads = [community(rng, 12, 24, 18) for _ in range(100)]
gens = [community(rng, 26, 24, 0) + family(rng) for _ in range(100)]
print("delta sock recall precision relatives others per genuine"
" false rate")
for delta in (0.10, 0.15, 0.20, 0.25, 0.30, 0.35):
tp = fp = rel = oth = 0
for pts in pads:
for i in flagged(pts, delta):
if i >= 12:
tp += 1
else:
fp += 1
for pts in gens:
for i in flagged(pts, delta):
if i >= 26:
rel += 1
else:
oth += 1
prec = tp / float(tp + fp) if tp + fp else 0.0
print("%.2f %.3f %.3f %.3f %.4f %.2f %.4f"
% (delta, tp / 1800.0, prec, rel / 400.0, oth / 2600.0,
(rel + oth) / 100.0, (rel + oth) / 3000.0))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《持续同调拓扑贝蒂数、高净值私域社群结构空洞与虚假抱团水军识别母典》第 5 章「嫌疑名单:零维短条码、伪装与基础比率」(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-236 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026236,
author = {Fan, Yafu},
title = {Persistent Homology and Betti Numbers: Structural Voids in High-Net-Worth Private Communities and the Review of Fake Cliques},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}