Tokenized Data Markets
This work addresses the challenge of decentralized data organization for machine learning and AI developers, though it appears incremental as it builds on existing concepts like token curated registries.
The paper tackles the problem of creating decentralized data markets by introducing tokenized data structures, a new incentivized data structure that unifies models for assembling complex data with multiple agents, and demonstrates their application in instantiating such markets.
We formalize the construction of decentralized data markets by introducing the mathematical construction of tokenized data structures, a new form of incentivized data structure. These structures both specialize and extend past work on token curated registries and distributed data structures. They provide a unified model for reasoning about complex data structures assembled by multiple agents with differing incentives. We introduce a number of examples of tokenized data structures and introduce a simple mathematical framework for analyzing their properties. We demonstrate how tokenized data structures can be used to instantiate a decentralized, tokenized data market, and conclude by discussing how such decentralized markets could prove fruitful for the further development of machine learning and AI.