mirror of
https://github.com/zoo-apps/papers.git
synced 2026-10-30 14:56:54 +00:00
Bylines, paper authorship, correspondence addresses and the founder blurb under each post named an individual. They name the organisation that published the work instead: the brand on posts and pages, the research byline on papers, and research@ in place of a personal address. Both are what these repositories already used elsewhere — nothing new was coined. Co-authors are untouched. Where a paper named someone else alongside, they stay named; only the one byline changed. Bibliography entries, running heads, PDF metadata and affiliations move with it, so a citation still resolves to whoever the cited paper names. Sample and fixture data uses the placeholder name these tests already use elsewhere, so no assertion changed meaning. Co-authored-by: Hanzo Dev <[email protected]>
83 lines
3.2 KiB
TeX
83 lines
3.2 KiB
TeX
\documentclass[11pt,letterpaper]{article}
|
|
\usepackage{shared/zoocover}
|
|
|
|
% Packages
|
|
\usepackage[utf8]{inputenc}
|
|
\usepackage[T1]{fontenc}
|
|
\usepackage{amsmath,amssymb,amsthm}
|
|
\usepackage{algorithm}
|
|
\usepackage{algorithmic}
|
|
\usepackage{graphicx}
|
|
\usepackage{hyperref}
|
|
\usepackage{multirow}
|
|
\usepackage{xcolor}
|
|
\usepackage{booktabs}
|
|
\usepackage{tikz}
|
|
\usetikzlibrary{shapes,arrows,positioning}
|
|
\usepackage{listings}
|
|
\input{shared/lstlang}
|
|
\usepackage{caption}
|
|
\usepackage{subcaption}
|
|
|
|
% Theorem environments
|
|
\newtheorem{theorem}{Theorem}[section]
|
|
\newtheorem{lemma}[theorem]{Lemma}
|
|
\newtheorem{proposition}[theorem]{Proposition}
|
|
\newtheorem{corollary}[theorem]{Corollary}
|
|
\newtheorem{definition}{Definition}[section]
|
|
\newtheorem{example}{Example}[section]
|
|
|
|
% Custom commands
|
|
\newcommand{\Zoo}{\textsc{Zoo}}
|
|
\newcommand{\HLLM}{\textsc{hllm}}
|
|
\newcommand{\DSO}{\textsc{dso}}
|
|
\newcommand{\DAO}{\textsc{dao}}
|
|
\newcommand{\IPFS}{\textsc{ipfs}}
|
|
\newcommand{\LLM}{\textsc{llm}}
|
|
|
|
% Hyperref setup
|
|
\hypersetup{
|
|
colorlinks=true,
|
|
linkcolor=blue,
|
|
citecolor=blue,
|
|
urlcolor=blue
|
|
}
|
|
|
|
% Title and authors
|
|
\title{\textbf{Experience Ledger: Decentralized Semantic Optimization for Large Language Models}}
|
|
\author{
|
|
Antje Worring, Zoo Labs Foundation Research\thanks{[email protected]}\\
|
|
\textit{Hanzo Industries \quad Lux Industries \quad Zoo Labs Foundation}\\
|
|
\texttt{[email protected]}
|
|
}
|
|
|
|
\date{September 2025}
|
|
|
|
\begin{document}
|
|
|
|
\zoocoverpage
|
|
|
|
\begin{abstract}
|
|
We present the \textit{Experience Ledger}, a decentralized infrastructure for semantic optimization of Large Language Models (\LLM{}s) that replaces centralized fine-tuning with community-driven knowledge curation. Unlike traditional approaches that update model parameters—an opaque, expensive, and centralized process—our system maintains a content-addressable library of semantic advantages: natural language insights extracted via introspection that guide model behavior through context injection. The Experience Ledger combines cryptographic verification (Merkle trees), decentralized storage (\IPFS{}/Arweave), and \DAO{}-based governance to enable transparent, auditable, and democratic model evolution. We demonstrate that semantic optimization achieves comparable or superior performance to parameter fine-tuning at 0.2\% of the cost while enabling cross-domain transfer, interpretability, and Byzantine-robust aggregation. This paradigm shift—from implicit weight updates to explicit wisdom commons—establishes a foundation for truly decentralized artificial intelligence.
|
|
\end{abstract}
|
|
|
|
\input{sections/01-introduction}
|
|
\input{sections/02-background-and-related-work}
|
|
\input{sections/03-experience-format-specification}
|
|
\input{sections/04-storage-architecture}
|
|
\input{sections/05-retrieval-system}
|
|
\input{sections/06-curation-protocol}
|
|
\input{sections/07-decentralized-semantic-optimization-algo}
|
|
\input{sections/08-evaluation}
|
|
\input{sections/09-comparison-with-alternative-approaches}
|
|
\input{sections/10-economic-model}
|
|
\input{sections/11-security-and-adversarial-robustness}
|
|
\input{sections/12-future-directions}
|
|
\input{sections/13-conclusion}
|
|
\input{sections/15-full-json-schemas}
|
|
\input{sections/16-smart-contract-abi}
|
|
\input{sections/17-prompt-templates}
|
|
\input{sections/99-acknowledgments}
|
|
|
|
\end{document}
|