SOURCE-LINKED INTELLIGENCE

On The Robustness-Resolution Tradeoff In Temporal Quantization Of Event Streams

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Event pipelines often discretize asynchronous timestamps before learning. This step looks harmless, but its stability depends directly on temporal resolution. We study this dependence at the representation level. We first show that hard temporal binning is discontinuous: an arbitrarily small timestamp shift near a boundary can move unit event mass between bins. We then define a class of nonnegative, mass-preserving, resolution-faithful continuous encoders and prove that every encoder in this class has global L1 sensitivity at least 2/Delta, where Delta denotes bin width. Linear two-bin interpo

Read original source ↗ Open in workspace

recordType

paper

region

Global