What does Link Authority, Retrieval Truncation and Direct Answers conclude, in numbers, about “Signal-to-Noise and Softmax Reranking: the Selection Gain of Direct-Answer Snippets”?
Answer: Chapter 6, the core of the book, derives the selection gain of a direct-answer snippet in a softmax reranker: with twenty candidates at temperature one the gain is 4.65; structured elements lift the probability of selection to 0.5866 while rivals rarely adopt them, and to only 0.1204 once rivals adopt them widely.
Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; the book is not personalised legal, financial or business advice and makes no promise about citation rankings in any system. Chapter 1 computes PageRank and HITS with power iteration and a random surfer: in an illustrative knowledge base with damping factor 0.85, the mother page receives 0.3240, or 2.59 times the uniform share.
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: 0.1204, 0.5866
| our snippet has | q=0.1 | q=0.5 | q=0.9 |
| none | 0.0681 | 0.0184 | 0.0068 |
| definition | 0.1939 | 0.0584 | 0.0222 |
| number | 0.1393 | 0.0400 | 0.0150 |
| source | 0.1648 | 0.0484 | 0.0182 |
| all three | 0.5866 | 0.2687 | 0.1204 |
| gain of all three over none: q=0.1: 8.62 x | q=0.5: 14.59 x | q=0.9: 17.75 x |
Key formula
Show the full program
# Chapter 6. p63: is a definition, a number or a named source worth it?
# Ten snippets compete for one citation; the reranker picks with chance
# proportional to exp(score / 0.5). Score = 0.6 if the snippet has a
# one-sentence definition + 0.4 if it states a number with its unit +
# 0.5 if it names its source (weights illustrative, not measured).
# Each of the nine rivals carries each feature independently with
# chance q (the adoption rate). Our snippet's expected chance of being
# cited is estimated over 40,000 fixed-seed draws of the rivals.
import math
import random
W = {"def": 0.6, "num": 0.4, "src": 0.5}
TAU = 0.5
RIVALS = 9
def our_chance(feats, q, draws, rng):
mine = math.exp(math.fsum(W[f] for f in feats) / TAU)
acc = []
for _ in range(draws):
rest = []
for _ in range(RIVALS):
s = math.fsum(W[f] for f in W if rng.random() < q)
rest.append(math.exp(s / TAU))
acc.append(mine / (mine + math.fsum(rest)))
return math.fsum(acc) / draws
if __name__ == "__main__":
sets = [(), ("def",), ("num",), ("src",), ("def", "num", "src")]
names = ["none", "definition", "number", "source", "all three"]
qs = (0.1, 0.5, 0.9)
print("our snippet has " + "".join(
" q={:.1f} ".format(q) for q in qs))
table = {}
for feats, name in zip(sets, names):
row = []
for q in qs:
rng = random.Random(20261112)
row.append(our_chance(feats, q, 40000, rng))
table[name] = row
print("{:<16}".format(name)
+ "".join("{:11.4f}".format(x) for x in row))
print("gain of all three over none: " + " ".join(
"q={:.1f}: {:.2f} x".format(q, a / b) for q, a, b in zip(
qs, table["all three"], table["none"])))Single source and citation
Fan, Y. (2026). Hyperlink Authority Propagation in Machine-Readable Knowledge Bases, Retrieval-Truncation Games in Generative Answering and High-SNR Snippet Extraction (Version 1.0.0), Chapter 6: Signal-to-Noise and Softmax Reranking: the Selection Gain of Direct-Answer Snippets. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-176 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026176,
author = {Fan, Yafu},
title = {Hyperlink Authority Propagation in Machine-Readable Knowledge Bases, Retrieval-Truncation Games in Generative Answering and High-SNR Snippet Extraction},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Power Iteration and the Damping Factor: How Hyperlink Authority Flows Through a Knowledge Base
- Chapter 2 · The Mother Page: How Internal-Link Topology Concentrates Authority
- Chapter 3 · BM25 and Length Normalisation: the Term-Frequency Ledger of Stuffing, Padding and Direct Answers
- Chapter 4 · Top-k Truncation: the Probability that a Passage Enters the Context
- Chapter 5 · Competing for k Positions: Position Auctions, Homogenisation and the Commons
- Chapter 7 · The Classics Examined: Zheng Qiao's Classification and Bush's Associative Trails
- Chapter 8 · Practice and Falsification: the Copy Checker, a Publisher's Checklist and a Pre-Registered Test