Reproduce “EasyTPP: Towards Open Benchmarking Temporal Point Processes” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Siqiao Xue, Xiaoming Shi, Zhixuan Chu, Yan Wang, Hongyan Hao, Fan Zhou, Caigao Jiang, Chen Pan and 4 more
EasyTPP provides a shared workflow for developing and comparing temporal point process models, which predict event timing and type from event history. It connects data preparation, training, sampling, evaluation, and tuning through common interfaces. Across nine models and six datasets, results vary by task and dataset, with no universal winner; these experiments assess prediction, not workflow efficiency.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.