Benchmark RadarAI BENCHMARK PROFILE
HyperShadow
HyperShadow evaluates binary classification of 3D point clouds as either native 3D objects or 3D projections of objects in 4-6 spatial dimensions, with static and temporal tracks, four corruption tiers, and fixed train/eval splits.
- Released
- 2026-07-15
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Addresses a gap in benchmarks for high-dimensional geometric data, providing a controlled testbed for studying projection signatures and out-of-distribution detection without physical reality claims.
Motivation
Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.