关于「距离先于拓扑:Jaccard 距离、类间缝隙与条码稳定性」,《社群拓扑体检》给出的定量结论是什么?

结论:条码在距离之上,距离要先过关。本书只用「成员参与过哪些帖子」这一张表,不用次数、正文与身份。互刷账号之间的 Jaccard 距离中位数是 0.152,真实成员到最近邻的中位数是 0.472,两类之间只有 0.333 到 0.344 的一条窄缝。稳定性定理保证每个距离只动 ε 时零维条码最多动 ε,L3 最多动 6ε;换成余弦距离,L3 的 AUC 从 0.983 变成 0.980,几乎不变,零维报警线却必须重定。下一个问题是:一根一维条要多长,才不是噪声?没有比较对象,「长」字没有意义,第四章用置换零模型给出比较对象。

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。

English version

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: 0.152, 0.333, 0.344, 0.472

classpairsJaccard min/med/maxcosine min/med/max
sock-sock pairs1530.000 0.152 0.3330.000 0.082 0.200
real-sock pairs2160.788 0.865 0.9560.651 0.762 0.915
real nearest neighbour300.344 0.472 0.6290.207 0.309 0.441
all real-real pairs4350.344 0.927 1.0000.207 0.864 1.000
gap between classes (Jaccard): 0.333 to 0.344
查看完整验算程序
# Chapter 3. p31: How far apart are lockstep accounts and real neighbours?
# One padded community (12 real members, 18 lockstep accounts) and one
# genuine community (30 members), fixed seed, synthetic only. Two
# distances on liked-post sets: Jaccard 1 - |A&B|/|A|B| and the cosine
# distance of 0/1 vectors 1 - |A&B|/sqrt(|A||B|). For real members we
# report each one's nearest neighbour, since rings are built from those.
import math
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 cosine(a, b):
    return 1.0 - len(a & b) / math.sqrt(len(a) * len(b))


def q3(vals):
    v = sorted(vals)
    return v[0], v[len(v) // 2], v[-1]


rng = random.Random(20261113)
gen = community(rng, 30, 24, 0)
pad = community(rng, 12, 24, 18)
classes = []
ss = [(pad[i], pad[j]) for i in range(12, 30) for j in range(i + 1, 30)]
classes.append(("sock-sock pairs", ss))
rs = [(pad[i], pad[j]) for i in range(12) for j in range(12, 30)]
classes.append(("real-sock pairs", rs))
nn = []
for i in range(30):
    j = min((k for k in range(30) if k != i),
            key=lambda k: (jaccard(gen[i], gen[k]), k))
    nn.append((gen[i], gen[j]))
classes.append(("real nearest neighbour", nn))
far = [(gen[i], gen[j]) for i in range(30) for j in range(i + 1, 30)]
classes.append(("all real-real pairs", far))
print("%-24s %5s  %-20s %-20s" % ("class", "pairs", "Jaccard min/med/max",
                                 "cosine min/med/max"))
for name, prs in classes:
    j3 = q3([jaccard(a, b) for a, b in prs])
    c3 = q3([cosine(a, b) for a, b in prs])
    print("%-24s %5d  %.3f %.3f %.3f    %.3f %.3f %.3f"
          % ((name, len(prs)) + j3 + c3))
lo = max(jaccard(a, b) for a, b in ss)
hi = min(jaccard(a, b) for a, b in nn)
print("gap between classes (Jaccard): %.3f to %.3f" % (lo, hi))

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 3 章「距离先于拓扑:Jaccard 距离、类间缝隙与条码稳定性」(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}
}

本书其他章节结论