关于「月度体检:掏空过程的条码时间序列与计算规模」,《社群拓扑体检》给出的定量结论是什么?
结论:第六章做十二个月的掏空序列,点赞维持在基线的 0.998 倍,同步报警与环的报警先后响起。
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: 0.998
| month | real | socks | likes | L3 | below | short | alarm |
| 1 | 30 | 0 | 880 | 0.1800 | no | 0.000 | - |
| 2 | 30 | 0 | 864 | 0.2357 | no | 0.000 | - |
| 3 | 30 | 0 | 850 | 0.2369 | no | 0.000 | - |
| 4 | 30 | 0 | 856 | 0.3197 | no | 0.000 | - |
| 5 | 30 | 0 | 883 | 0.2452 | no | 0.000 | - |
| 6 | 30 | 0 | 872 | 0.1981 | no | 0.000 | - |
| baseline L3 mean 0.2359, sd 0.0483, floor 0.1393 | |||||||
| 7 | 27 | 3 | 859 | 0.2527 | no | 0.067 | - |
| 8 | 24 | 6 | 912 | 0.1142 | yes | 0.167 | lockstep |
| 9 | 21 | 9 | 867 | 0.1505 | yes | 0.267 | lockstep |
| 10 | 18 | 12 | 886 | 0.1389 | yes | 0.367 | ring+lockstep |
| 11 | 15 | 15 | 886 | 0.1026 | yes | 0.467 | ring+lockstep |
| 12 | 12 | 18 | 866 | 0.0413 | yes | 0.567 | ring+lockstep |
| likes, months 1-6 mean 867.5; month 12 / mean = 0.998 |
查看完整验算程序
# Chapter 6. p61: A twelve-month topological checkup with a hollowing.
# Months 1-6: 30 genuine members, each with a fixed interest arc; likes
# are redrawn every month. From month 7 three members leave and three
# lockstep accounts join each month, so head count and likes stay
# level. Ring alarm: L3 below the null line 0.1786 of p41 in this and
# the previous month, and below the months 1-6 mean minus 2 sd.
# Lockstep alarm: more than 0.10 short H0 bars per account (delta 0.2).
import math
import random
import statistics
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 lead3(h1):
# length of the three longest one-dimensional bars, added exactly
top = sorted((d - b for b, d in h1), reverse=True)[:3]
return math.fsum(top)
def short_frac(h0, n, delta=0.2):
# zero-dimensional bars dying below delta, per account
return len([1 for d, i, j in h0 if d < delta]) / float(n)
rng = random.Random(20261113)
prof = [(rng.uniform(0, 24), rng.randint(5, 8)) for _ in range(30)]
target = set(rng.sample(range(N_POSTS), 30))
LINE, SHORT = 0.1786, 0.10
print("month real socks likes L3 below short alarm")
base, below_prev, floor = [], False, None
for month in range(1, 13):
gone = max(0, 3 * (month - 6))
pts = [member(rng, c, w) for c, w in prof[gone:]]
pts += [sock(rng, target) for _ in range(gone)]
h0, h1 = barcodes(pts)
likes = int(math.fsum(len(p) for p in pts))
l3, sf = lead3(h1), short_frac(h0, len(pts))
below = l3 < LINE
flag = []
if month <= 6:
base.append((likes, l3))
else:
if below and below_prev and l3 < floor:
flag.append("ring")
if sf > SHORT:
flag.append("lockstep")
print("%5d %4d %5d %5d %.4f %-5s %.3f %s"
% (month, 30 - gone, gone, likes, l3, "yes" if below else "no",
sf, "+".join(flag) or "-"))
below_prev = below
if month == 6:
b3 = [x[1] for x in base]
floor = statistics.mean(b3) - 2 * statistics.stdev(b3)
print("baseline L3 mean %.4f, sd %.4f, floor %.4f"
% (statistics.mean(b3), statistics.stdev(b3), floor))
m = math.fsum(x[0] for x in base) / 6
print("likes, months 1-6 mean %.1f; month 12 / mean = %.3f"
% (m, likes / m))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 6 章「月度体检:掏空过程的条码时间序列与计算规模」(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}
}