统一评测时空事件建模，让不同模型公平比较。
Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
- 用编码-演化-解码框架统一神经时空过程模型
- 在真实与合成数据上实现一致的似然评估
- 适合研究模型偏差与可复现性的人看
时空点过程（STPPs）用于连续时空中的事件建模，应用涵盖出行、流行病学和公共安全。近年神经型STPP包含表达性强度模型、条件密度模型、连续时间潜在动态、归一化流空间解码器及基于得分的生成机制。但因预处理、坐标归一化、数据划分、似然约定和评估协议差异，模型对比难以可靠进行。本文提出SEAHORSE，一个可复现的STPP实验统一框架。SEAHORSE通过统一的编码-演化-解码接口形式化神经型STPP，并在单一可执行基准协议下训练、调参与评估所有模型家族，报告原始坐标似然。该框架支持公平比较，更关键的是可控诊断分析。我们配套推出HawkesNest合成压力测试套件，结果表明：随事件模式复杂度上升，各模型家族的归纳偏置暴露明显，部分模型性能急剧下降，而另一些保持稳定。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。