@techreport{chen-nmrg-semantic-inference-routing-00,
    number =    {draft-chen-nmrg-semantic-inference-routing-00},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-chen-nmrg-semantic-inference-routing/00/},
    author =    {Huamin Chen and Luay Jalil},
    title =     {{Semantic Inference Routing Protocol (SIRP)}},
    pagetotal = 12,
    year =      2025,
    month =     oct,
    day =       1,
    abstract =  {This document specifies the Semantic Inference Routing Protocol (SIRP), a framework for content-level classification and semantic routing in AI inference systems. By analyzing the content of inference requests--rather than relying solely on client-supplied metadata--SIRP enables routing decisions that are more robust, consistent, and extensible. SIRP also defines optional value-added routing (VAR) extensions for cost optimization, urgency prioritization, domain specialization, and privacy-aware handling.},
}