2026-10-13T19:43:09Z https://www.scidb.cn/oai

10.57760/sciencedb.39323 2026-06-11T15:14:12Z

2026-06-11 Causal Structure Uncertainty Benchmark – Synthetic Linear SEM Suite doi:10.57760/sciencedb.39323 en This dataset is a collection of synthetic data generated from linear structural equation models, designed for research on uncertainty and stability assessment in causal graph structure learning. It consists of independent and identically distributed samples under a variety of conditions, including different numbers of observed variables, graph densities, varying direct effect strengths, measurement noise levels, and finite sample sizes. All samples are produced from explicitly defined causal skeletons and complete orientation information, thereby providing known ground-truth causal structures while retaining the structural inference challenges that arise from finite-sample variability. The dataset can serve as a public benchmark for testing resampling-based diagnostic tools, evaluating methods that quantify structural uncertainty, and comparing the stability performance of different causal discovery algorithms. It is particularly suitable for broad analytical scenarios such as edge existence risk, orientation reproducibility, and overall structural uncertainty decomposition. causal graph; structural equation model; uncertainty benchmark Chi ZHANG RESTRICTED dataset Science Data Bank