5D Library › Retrodictive Belief Locking, Sequential Pain-Point Agitation and Markovian Upsell Automata · 中文
Chapter 8. A Calculator for the User and a Pre-Registered Blinded Test
Four questions for any reading service
This chapter turns the book into four questions that can be put to any reading service, the author’s own included. They are not marketing or business advice.
One: can its retrodictive statements be written down beforehand and checked afterwards? Generic statements are almost no evidence; only checkable details recorded in advance are (Chapters 1 and 2).
Two: are its upsell prices and timing well below the user’s resistance threshold and after she has felt a result? Pushing to the threshold does not pay (Chapter 3).
Three: does it have a cooling-off period and a distress screen? Without guardrails, stronger agitation raises the share of buyers in distress (Chapter 4).
Four: are its conversion forecasts segmented before chains are built, and do they state their uncertainty? One chain cannot hold two kinds of user, and rare transitions need tens of thousands of users to estimate (Chapter 6).
The user’s own calculator
After a reading, a user can count the retrodictive statements the reader made by kind – generic, semi-specific, checkable – with their hits and misses, and compute her posterior from her own prior.
Calculation
# Chapter 8. [p15] A calculator a client can run after a reading.
# She counts the reader's retrodictive statements about her past by
# kind, as hits and misses, and starts from her own prior (here 0.01).
# The true likelihood ratios are those of p01 (generic h 0.95, b 0.80;
# semi-specific 0.90, 0.30; checkable detail 0.90, 0.02); the "felt"
# posterior uses the Forer base rate 0.20 for generic statements and
# ignores misses. Example: 6 generic hits and 1 miss, 2 semi-specific
# hits and 1 miss, no checkable detail.
import math
KINDS = {"generic": (0.95, 0.80, 0.20),
"semi-specific": (0.90, 0.30, 0.30),
"checkable": (0.90, 0.02, 0.02)}
COUNTS = {"generic": (6, 1), "semi-specific": (2, 1), "checkable": (0, 0)}
PRIOR = 0.01
def posterior(true):
lo = math.log(PRIOR / (1 - PRIOR))
for k, (hits, misses) in COUNTS.items():
h, b, felt = KINDS[k]
bb = b if true else felt
lo += hits * math.log(h / bb)
if true:
lo += misses * math.log((1 - h) / (1 - b))
return 1 / (1 + math.exp(-lo))
if __name__ == "__main__":
for k, (hh, mm) in COUNTS.items():
print(" {:14s} hits {} misses {}".format(k, hh, mm))
print(" posterior of real insight, true ratios : {:.4f}".format(
posterior(True)))
print(" posterior as it feels (Forer, no misses): {:.4f}".format(
posterior(False)))
print("\nReading: the same reading that feels conclusive leaves a")
print("careful client almost where she started. Only checkable")
print("details, written down before they are checked, can move her.")
# generic hits 6 misses 1
# semi-specific hits 2 misses 1
# checkable hits 0 misses 0
# posterior of real insight, true ratios : 0.0090
# posterior as it feels (Forer, no misses): 0.9990
#
# Reading: the same reading that feels conclusive leaves a
# careful client almost where she started. Only checkable
# details, written down before they are checked, can move her.In the example, 6 generic statements hit and 1 missed, 2 semi-specific statements hit and 1 missed, and there was no checkable detail. With the true likelihood ratios the posterior probability of insight is 0.0090, lower than the prior of 0.01; by feel (Barnum base rate, misses ignored) it is 0.9990. The same reading feels almost certain and, on the evidence, leaves her almost where she began.
A pre-registered blinded test
Hypothesis · not established
Study protocol. A complete reading engine (rules for generating statements, wording templates) is registered publicly before recruitment and not changed afterwards. Each participant submits birth data; an independent analyst uses the registered engine to generate a set of retrodictive statements for the participant and for two other participants chosen at random. The participant, not knowing the sources, picks the set that best fits her past. Primary outcome: the share who pick the set generated for them; one in three without information. Test: one-sided exact binomial test, , power 0.90, alternative 0.45. Carried out by an independent analyst who has no financial relationship with the author and does not know the sources; results published whether positive or negative (Carlson 1985).
Calculation
# Chapter 8. [p16] A pre-registered blinded retrodiction test.
# Each participant gives birth data; an independent analyst runs the
# registered engine to write retrodictive statements for the
# participant and for two decoys (other participants' birth data). The
# participant, blind to the source, picks the set that fits her past.
# H0: hit rate 1/3. H1: 0.45. One-sided exact binomial test at 0.05,
# power 0.90: the smallest n and its critical number of hits.
from math import comb
def tails(n, p):
"""upper tails P(X >= k), k = 0..n, for X ~ Binomial(n, p)"""
pmf = [comb(n, j) * p ** j * (1 - p) ** (n - j) for j in range(n + 1)]
out, acc = [0.0] * (n + 2), 0.0
for j in range(n, -1, -1):
acc += pmf[j]
out[j] = acc
return out
def plan(p0, p1, alpha=0.05, power=0.90):
for n in range(20, 2000):
t0, t1 = tails(n, p0), tails(n, p1)
k = next(k for k in range(n + 1) if t0[k] <= alpha)
if t1[k] >= power:
return n, k, t0[k], t1[k]
if __name__ == "__main__":
n, k, a, b = plan(1 / 3, 0.45)
print(" participants {}, reject H0 at {} hits or more".format(n, k))
print(" size {:.4f}, power {:.4f}".format(a, b))
n2, k2, a2, b2 = plan(1 / 3, 0.40)
print(" for H1 = 0.40 instead: {} participants, {} hits".format(
n2, k2))
print("\nReading: a fair test of retrodiction is cheap: a few hundred")
print("participants. What makes it fair is the decoys, the blinding")
print("and the registration, not the size.")
# participants 152, reject H0 at 61 hits or more
# size 0.0468, power 0.9015
# for H1 = 0.40 instead: 447 participants, 166 hits
#
# Reading: a fair test of retrodiction is cheap: a few hundred
# participants. What makes it fair is the decoys, the blinding
# and the registration, not the size.With 0.45 as the alternative, 152 participants are needed, and 61 hits or more reject the null hypothesis; the actual size is 0.0468 and the power 0.9015. With the more cautious alternative of 0.40, 447 participants are needed. A fair test of retrodiction is not expensive; what makes it fair is the decoys, the blinding and the registration, not the sample size.
Summary
Four questions – can statements be checked, do upsells stay well below the threshold, are there guardrails, are forecasts segmented – can be put to any reading service. The user’s own calculator shows that a reading that “feels accurate” may barely move the prior on the evidence. A blinded test of retrodictive ability needs only 152 participants (alternative 0.45) to 447 (alternative 0.40).
References
Fan, Y. (2026). Retrodictive Belief Locking, Sequential Pain-Point Agitation and Markovian Upsell Automata: Bayesian Trust Avalanches, Sunk-Cost Commitment Ratchets and Cross-Domain Transition Matrices [回溯信念锁定、序贯痛点唤醒与马尔可夫升单自动机] (Version 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090186 · Licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).