关于「实证闭环:福袋页概率公示生成器、台马规范核对与预注册抽检」,《盲盒收集与福袋概率公示》给出的定量结论是什么?
结论:第八章给出福袋页概率公示生成器、蒸馏小工具「福袋概率公示器」、台湾与马来西亚规范核对表、预注册抽检方案(标称 1/144 对 1/288 需 2808 盒)与推翻本书核心命题的条件。书中以标注框区分已发表的证据、可运行的 Python 计算(23 段程序)、原典与作者的假说。
数据口径:书中参数为示意;全部计算由书中程序生成;本书是非个人化法律或理财建议,法条以上架前人工复核为准。 第一章用调和数、精确分布与固定种子模拟算等概率集齐;第二章用几何分布算隐藏款等待,并陈复合事件判断偏差的相反证据,说明保底只改变等待(保底 144 次时平均 91.21 次)而不改变标称概率;第三章用容斥公式与泊松化积分算不等概率,12 款加 1/144 隐藏款的全套期望是 149.07 盒;第四章用双杯问题算合买与重复款,以及开盒止损;第五章算福袋的期望、方差与低于售价的概率(示意福袋为 0.8280)以及小概率加权。
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: 144, 2808, 288
| stated | true | boxes n | reject if x <= | alpha | power |
|---|---|---|---|---|---|
| 1/144 | 1/288 | 2808 | 12 | 0.0482 | 0.8150 |
| 1/144 | 1/216 | 6864 | 36 | 0.0477 | 0.8020 |
| 1/144 | 1/180 | 20256 | 121 | 0.0499 | 0.8029 |
| 1/12 | 1/24 | 216 | 11 | 0.0477 | 0.8072 |
| cases of 12 for the 1/144 vs 1/288 audit: 234 |
查看完整验算程序
# Chapter 8. p82: how many boxes a pre-registered audit must open.
# H0: the hidden rate is the stated 1/144. H1: the true rate is lower.
# One-sided exact binomial test at alpha = 0.05: reject H0 when the count
# of hidden boxes x is at or below the largest c with P0(X <= c) <= 0.05.
# Power = P1(X <= c). Report the least n with power >= 0.80, scanning n
# in steps of 24 boxes (two sealed cases). Alternatives illustrative.
# Context for Chapter 8 (Xiao, Henderson, Yang and Newall, Behavioural
# Public Policy): in 100 top-grossing PRC iPhone games, 91 had loot
# boxes; disclosures could not be found for 0.044 of those, and only
# 0.055 used the most prominent format; 0.905 of 12+ games had them.
import math
def log_pmf(n, k, p):
return (math.lgamma(n + 1) - math.lgamma(k + 1) - math.lgamma(n - k + 1)
+ k * math.log(p) + (n - k) * math.log(1 - p))
def cdf(n, c, p):
return math.fsum(math.exp(log_pmf(n, k, p)) for k in range(c + 1))
def plan(p0, p1, alpha=0.05, power=0.80):
n = 24
while True:
c = -1
while cdf(n, c + 1, p0) <= alpha:
c += 1
if c >= 0 and cdf(n, c, p1) >= power:
return n, c, cdf(n, c, p0), cdf(n, c, p1)
n += 24
print("stated true boxes n reject if x <= alpha power")
for p0, p1, lab in ((1 / 144, 1 / 288, "1/288"), (1 / 144, 1 / 216, "1/216"),
(1 / 144, 1 / 180, "1/180"), (1 / 12, 1 / 24, "1/24 ")):
n, c, a, pw = plan(p0, p1)
s = "1/144" if p0 < 0.01 else "1/12 "
print("{} {} {:6d} {:4d} {:.4f} {:.4f}".format(
s, lab, n, c, a, pw))
print("cases of 12 for the 1/144 vs 1/288 audit: {:.0f}".format(
plan(1 / 144, 1 / 288)[0] / 12))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《盲盒收集券问题、隐藏款几何等待时间与福袋概率公示合规母典》第 8 章「实证闭环:福袋页概率公示生成器、台马规范核对与预注册抽检」(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-210 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026210,
author = {Fan, Yafu},
title = {Blind-Box Coupon Collecting, Geometric Waits for Hidden Variants and Odds Disclosure for Lucky Bags},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}