Benchmark RadarHawkesNest
HawkesNest is a synthetic benchmark for spatiotemporal point process models, providing controlled generators and complexity ladders across four axes: space-time entanglement, background heterogeneity, cross-type interaction, and domain topology. It includes simulation, export, and visualization tools.
- Released
- 2026-06-15
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Real-world spatiotemporal event datasets obscure generative structure, making model failures hard to attribute. HawkesNest isolates complexity factors for diagnostic stress tests, enabling controlled evaluation of STPP models under known structural difficulty.
Motivation
Evaluation of spatiotemporal point process (STPP) models relies heavily on opaque real-world datasets, where latent generative structure is unknown and model failures are difficult to attribute.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.