Matoi, described in a new arXiv preprint, is a mechanism for agent authorization that separates reusable consequence evidence from current execution authority and durable occurrence history. The abstract states that a consumer reuses only its…, but the sentence is cut off in the available text. The paper's title emphasizes "selective revalidation," suggesting that not all consequence evidence needs to be rechecked on every authorization decision.

The abstract also specifies a "finite query-aware contract" that covers branches, ordered collections, and negative lookups. This contract appears to define the kinds of queries for which consequence evidence can be reused. Because the abstract is truncated, the precise mechanics of how the consumer selects which evidence to reuse are not fully described in the available text.

The source is a single abstract, so the details beyond these components are limited. No independent evaluation or comparison with other authorization mechanisms is provided in the excerpt.