mirror of
https://github.com/zoo-apps/papers.git
synced 2026-10-30 14:56:54 +00:00
zeekayandHanzo Dev
dced1dcfb9
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]>
80 lines
3.4 KiB
TeX
80 lines
3.4 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{xcolor}
|
|
\usepackage{booktabs}
|
|
\usepackage{tikz}
|
|
\usepackage{pgfplots}
|
|
\pgfplotsset{compat=1.18}
|
|
\usetikzlibrary{shapes,arrows,positioning,calc}
|
|
\usepackage{listings}
|
|
\input{shared/lstlang}
|
|
\usepackage{caption}
|
|
\usepackage{subcaption}
|
|
% geometry loaded by zoocover
|
|
|
|
% 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{\IPFS}{\textsc{ipfs}}
|
|
\newcommand{\LLM}{\textsc{llm}}
|
|
|
|
% Hyperref setup
|
|
\hypersetup{
|
|
colorlinks=true,
|
|
linkcolor=blue,
|
|
citecolor=blue,
|
|
urlcolor=blue
|
|
}
|
|
|
|
% Title and authors
|
|
\title{\textbf{Zoo Experience Ledger: A Content-Addressable Semantic Memory System for Decentralized AI}}
|
|
\author{
|
|
Antje Worring, Zoo Labs Foundation Research\thanks{[email protected]}\\
|
|
\textit{Hanzo Industries \quad Lux Industries \quad Zoo Labs Foundation}\\
|
|
\texttt{[email protected]}
|
|
}
|
|
|
|
\date{October 2021}
|
|
|
|
\begin{document}
|
|
|
|
\zoocoverpage
|
|
|
|
\begin{abstract}
|
|
We present the \textbf{Zoo Experience Ledger}, a content-addressable semantic memory system designed for decentralized AI agents. Originally proposed in the Zoo whitepaper (October 2021)---thirteen months before OpenAI's ChatGPT (November 2022) and well before vector databases entered mainstream adoption---the Experience Ledger stores AI reasoning patterns as cryptographically-verified semantic objects distributed across \IPFS{} and permanent storage networks. Each experience---a natural language encoding of a successful problem-solving strategy---is uniquely identified by its content hash, enabling tamper-evident storage and peer-to-peer distribution. We introduce a novel Merkle-DAG structure optimized for semantic similarity queries, achieving $O(\log n)$ retrieval complexity while maintaining cryptographic integrity proofs. The experience token model provides persistent conversational memory anchored to on-chain identity---a capability that commercial \LLM{} chat products did not offer until 2024. Our system enables AI agents to share learned experiences across organizational boundaries without trust assumptions, creating the foundation for a global semantic commons. Experimental evaluation demonstrates 94.7\% retrieval accuracy with sub-second latency on libraries of 10,000+ experiences, while reducing storage costs by 89\% compared to traditional vector databases through content deduplication.
|
|
|
|
\textbf{Keywords}: content-addressable storage, semantic memory, IPFS, Merkle trees, AI knowledge sharing
|
|
\end{abstract}
|
|
|
|
\input{sections/01-introduction}
|
|
\input{sections/02-background}
|
|
\input{sections/03-experience-format-specification}
|
|
\input{sections/04-merkle-dag-architecture}
|
|
\input{sections/05-retrieval-protocol}
|
|
\input{sections/06-storage-architecture}
|
|
\input{sections/07-experimental-evaluation}
|
|
\input{sections/08-security-analysis}
|
|
\input{sections/09-related-work}
|
|
\input{sections/10-conclusion}
|
|
\input{sections/12-experience-format-json-schema}
|
|
\input{sections/13-ipld-schema}
|
|
\input{sections/99-acknowledgments}
|
|
|
|
\end{document}
|