SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation
Summary: SAGA decouples O(1)-per-edge power-law skeleton generation from LLM/RAG semantic injection over causally ordered temporal blocks. Temporal replay aligns state and yields ground-truth anomaly labels for scalable, multi-domain temporal graph benchmarks. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jiacheng Ding (University of Memphis)
- 2. Xiaofei Zhang (University of Memphis)
BibTeX Citation
@article{ding_vldb26,
title = {{SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation}},
author = {Ding, Jiacheng and Zhang, Xiaofei},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4834--4837},
doi = {10.14778/3827998.3828134},
url = {https://doi.org/10.14778/3827998.3828134},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 387 | The LDBC Social Network Benchmark: Interactive Workload | 2015 | SIGMOD | 0.00019426275 |
| 4,895 | TrillionG: A Trillion-scale Synthetic Graph Generator using a Recursive Vector Model | 2017 | SIGMOD | 6.3670408e-05 |
Previous
Page 1 / 1
Next