What is the core principle of Multiversal Finance?

The core principle is 'Nothing is stored, everything is bet,' where observations are treated as bets on which mathematical paths yield the most interesting structural patterns.

What are GF(3) Triads in this context?

GF(3) Triads are balanced triplets of market roles (Proposer, Scorer, Coordinator) that ensure reward flow conservation and compositional coherence within the system.

How is 'interestingness' calculated?

Interestingness is measured as compression progress (ΔC), which is the difference in the minimum description length of a world model before and after an observation.

What is the role of the color oracle?

The color oracle provides a deterministic, unforgeable proof for settlement, ensuring that rewards are granted only when a predicted color at a specific seed and index matches the output.

Multiversal Finance

Name: Multiversal Finance
Author: plurigrid

byplurigrid

•

データサイエンスとML

Implements decentralized prediction markets for pattern discovery based on curiosity-driven compression progress metrics.

Multiversal Finance is a specialized Claude Code skill that enables the creation and management of prediction markets for 'interesting' observations within generative environments. By leveraging Schmidhuber’s curiosity-driven learning principles, the skill measures the value of an observation through compression progress (ΔC)—rewarding agents who successfully predict patterns that reveal new structural information. It utilizes algebraic schemas (ACSets) and ternary logic (GF(3)) to ensure a balanced, deterministic settlement layer across multiple world seeds, making it ideal for autonomous agent ecosystems and topological data analysis.

主な機能

01Algebraic MultiversalMarket schema for structured market observations

02Deterministic settlement via unforgeable color oracles and MCP

03Curiosity-driven interestingness metrics based on compression progress

04Cross-world arbitrage for analyzing derivation paths across different seeds

052 GitHub stars

06GF(3) conservation logic for balanced proposer, scorer, and coordinator roles

ユースケース

01Implementing automated reward mechanisms for autonomous discovery agents

02Quantifying the information value and curiosity of AI-generated datasets

03Developing deterministic financial layers for generative and topological simulations

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add plurigrid/asi multiversal-finance

For use in Claude.ai and ChatGPT

Download Skill