Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
For researchers in spatiotemporal event modeling, SEAHORSE provides a standardized evaluation protocol to address the lack of reproducibility and fair comparison in the field.
The paper introduces SEAHORSE, a unified benchmarking framework for spatiotemporal point processes, enabling fair comparisons and diagnostic studies across model families. Using the synthetic HawkesNest suite, it reveals how increasing event-pattern complexity exposes inductive biases, with some models degrading sharply while others remain stable.
Spatiotemporal point processes (STPPs) model event data in continuous time and space, with applications in mobility, epidemiology, and public safety. Recent neural STPPs span expressive intensity models, conditional density models, continuous-time latent dynamics, normalizing-flow spatial decoders, and score-based generative mechanisms. Yet comparison remains fragile because implementations differ in preprocessing, coordinate normalization, splits, likelihood conventions, and evaluation protocols. We present SEAHORSE, a unified framework for reproducible STPP experimentation. SEAHORSE formalizes neural STPPs through a common encode-evolve-decode interface and trains, tunes, and evaluates every model family under a single executable benchmark protocol with raw-coordinate likelihood reporting. This enables fair comparisons but, more importantly, controlled diagnostic studies. We pair SEAHORSE with HawkesNest, a synthetic stress-test suite, and show that increasing event-pattern complexity exposes each family's inductive bias, degrading some models sharply and leaving others stable. Code: https://github.com/YahyaAalaila/seahorse.