Model Routing as a Trust Problem: Route Receipts for Adaptive AI Systems
For users and auditors of AI systems, this work addresses the problem of opaque routing decisions that affect trust, but it is an incremental conceptual contribution without empirical validation.
The paper introduces route receipts as a transparency artifact for adaptive AI systems, capturing runtime routing decisions to address trust issues when routing changes cost, quality, or accountability. It proposes a minimal schema and redaction model, and surveys existing platforms to show that receipt fragments exist but lack a portable per-answer record.
AI products often route requests through version aliases, service tiers, tool choices, regional endpoints, fallback rules, or safety handling before responding. These routing steps are documented product surfaces in several widely used AI platforms and serving stacks. Routing helps AI services stay affordable, fast, and available at scale, and it shapes trust. Trust can break when routing changes the cost, quality, or accountability of a response without the user being able to tell what happened. "Which model answered?" is only part of the audit question. The runtime path matters. Adaptive AI systems should produce a runtime transparency artifact called the route receipt. A route receipt is a compact record of the route that served a request. It should capture enough material facts for people relying on the output to reconstruct important routing decisions without exposing proprietary internals or hidden reasoning. Route transparency should be part of model documentation. Model cards describe trained model artifacts, while route receipts describe the runtime conditions under which a particular answer was produced. The paper introduces the route-receipt concept, a minimal schema and redaction model, and a documentation-based survey of selected platforms showing that receipt fragments already exist without a portable per-answer record.