# From Leakage to Fidelity: Reliable Benchmarking for Temporal Cascade Prediction

arXiv: https://arxiv.org/abs/2510.25348 · HTML: https://mlsanity.com/paper/2510.25348/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks](https://mlsanity.com/paper/1701.05923/) (2017)
- [APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding](https://mlsanity.com/paper/2011.11545/) (2020)
- [DeepCas: an End-to-end Predictor of Information Cascades](https://mlsanity.com/paper/1611.05373/) (2016)
- [Can Cascades be Predicted?](https://mlsanity.com/paper/1403.4608/) (2014)
- [Improving Temporal Link Prediction via Temporal Walk Matrix Projection](https://mlsanity.com/paper/2410.04013/) (2024)
- [Learning to Recommend with Multiple Cascading Behaviors](https://mlsanity.com/paper/1809.08161/) (2018)
- [Virality Prediction and Community Structure in Social Networks](https://mlsanity.com/paper/1306.0158/) (2013)
- [SAGraph: A Large-Scale Social Graph Dataset with Comprehensive Context for Influencer Selection in Marketing](https://mlsanity.com/paper/2403.15105/) (2024)

## Built on by (most cited first, 2 of 2)

- [Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generation](https://mlsanity.com/paper/2607.21101/) (2026)
- [Network World Models as Environments for Algorithm Design on Complex Systems](https://mlsanity.com/paper/2610.01048/) (2026)

## Abstract (arXiv)

Temporal cascade prediction is widely studied, yet its empirical foundations remain fragile. Most existing works report results under random cascade splits that mix past and future signals, rely on datasets with limited features and no downstream conversion labels, and compare increasingly complex models without systematically examining whether benchmark conclusions are protocol-dependent. This paper argues that the field should move from leakage-prone evaluation toward fidelity-aware benchmarking. We introduce a protocol suite and renewed evaluation standard for temporal cascade prediction, centered on the Full Temporal protocol, overlap-based leakage diagnostics, and analyses of performance inflation and temporal drift. To broaden the scope of benchmark tasks, we also present Taoke, a real-world e-commerce cascade dataset with rich promoter/product features and observed purchase conversions, enabling both first-stage popularity forecasting and second-stage conversion forecasting under a shared benchmark asset. Finally, we include CasTemp as a lightweight reference method and additionally probe a larger same-task internal extension to verify that this pipeline remains operational at substantially greater scale. Together, these components turn cascade prediction from a protocol-sensitive leaderboard exercise into a more reliable analysis and benchmarking problem, while still providing a practical reference pipeline for large-scale evaluation and conversion-aware modeling.