What does Hard Gates and Soft-Prompt Decay conclude, in numbers, about “Decay over Turns: an Exponential Model of Soft-Prompt Compliance, Re-Sending Periods and Reading the Log”?
Answer: Chapter 3 gives an exponential decay model with a floor, with a half-life of 6.93 turns, under which a forty-turn session lets through 4.71 times the static estimate.
Scope of the numbers: Soft reminders work in proportion; when layers are independent the residual violation rate is the product of their miss rates, and with illustrative parameters four layers still leave 0.0048, not zero. Its parameters are illustrative; all calculations are generated by its programs.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 4.71, 6.93
| half-life of the excess compliance ln2/k | 6.93 turns |
| turn comply miss | |
| 0 | 0.9500 0.0500 |
| 5 | 0.8516 0.1484 |
| 10 | 0.7920 0.2080 |
| 20 | 0.7338 0.2662 |
| 40 | 0.7046 0.2954 |
| 80 | 0.7001 0.2999 |
| expected escapes per session, decaying versus static model: | |
| T | 10 decaying 0.134 static 0.050 ratio 2.68 |
| T | 40 decaying 0.942 static 0.200 ratio 4.71 |
| T | 100 decaying 2.737 static 0.500 ratio 5.47 |
Key formula
Show the full program
# Chapter 3. p31: a soft prompt whose pull fades with the turns.
# Author's working model (a hypothesis, not a published law): the
# chance that the agent follows a standing instruction at turn t is
# c(t) = c_inf + (c0 - c_inf) x exp(-k t),
# starting at c0 and sinking to a floor c_inf. Illustrative values:
# c0 = 0.95, c_inf = 0.70, k = 0.10 per turn. Each turn offers a
# violation opportunity with probability v = 0.10, as in p11.
import math
C0, CINF, K, V = 0.95, 0.70, 0.10, 0.10
def comply(t):
return CINF + (C0 - CINF) * math.exp(-K * t)
print("half-life of the excess compliance ln2/k = %.2f turns"
% (math.log(2) / K))
print("%5s %10s %10s" % ("turn", "comply", "miss"))
for t in (0, 5, 10, 20, 40, 80):
print("%5d %10.4f %10.4f" % (t, comply(t), 1 - comply(t)))
print("expected escapes per session, decaying versus static model:")
for T in (10, 40, 100):
dec = math.fsum(V * (1 - comply(t)) for t in range(T))
sta = V * (1 - C0) * T
print(" T = %3d decaying %.3f static %.3f ratio %.2f" % (
T, dec, sta, dec / sta))Single source and citation
Fan, Y. (2026). Hard Gates across the Client Lifecycle: the Decay of Soft-Prompt Compliance over Turns and State Machines for Interception before Publication (Version 1.0.0), Chapter 3: Decay over Turns: an Exponential Model of Soft-Prompt Compliance, Re-Sending Periods and Reading the Log. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-256 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026256,
author = {Fan, Yafu},
title = {Hard Gates across the Client Lifecycle: the Decay of Soft-Prompt Compliance over Turns and State Machines for Interception before Publication},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · The Product Account: Why Stacked Soft Layers Never Leave a Zero Residual
- Chapter 2 · Holes That Line Up: the Floor That Common-Cause Failure Puts under Stacked Soft Layers
- Chapter 4 · Where to Intercept: before the Write, after It or before Publication, and Whether a Broken Gate Passes or Refuses
- Chapter 5 · Exhausting the State Machine: Proving a Dirty Publication Unreachable and Finding the Shortest Counterexamples of Three Faulty Designs
- Chapter 6 · The Price of Hardness: Pattern Width, Wrong Blocks and Gates That Get Switched Off
- Chapter 7 · Classical Sources East and West: Law and the Inked Line in the Han Feizi, and Reason's Classification of Error
- Chapter 8 · Closing the Loop: the Weekly Interception Report, the Residual Calculator and a Pre-Registered Test