Cognitive Oracles: Provable on-chain assessment through Validity Machine Learning

Blockchains offer a mechanism for executing code in a credible, transparent and uncensorable way. These characteristics lend themselves to the implementation of applications that guarantee different actors regarding the credible execution of mechanisms, including insurance and impartial certification. A significant challenge in this domain is enabling smart contracts to reliably access real-world state information. Our research centers on scenarios requiring smart contracts to evaluate complex or ambiguous conditions, such as identifying specific elements within an image. The proposed solution introduces an oracle utilizing machine learning classifiers to aid smart contracts in assessing such intricate predicates. We incorporate SNARK arguments to facilitate efficient and secure evaluation of these classifiers, and introduce a jury-based system to address classifier inaccuracies. We evaluate the proposed architecture with respect to an example application.