AI RESEARCH
The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive
arXiv CS.CL
•
ArXi:2604.25634v1 Announce Type: cross We report a striking statistical regularity in frontier LLM outputs that enables a CPU-only scoring primitive running at 2.6 microseconds per token, with estimated latency up to 100,000$\times$ (five orders of magnitude) below existing sampling-based detectors.