Causal-Audit: A Framework for Risk Assessment of Assumption Violations in Time-Series Causal Discovery
Not on the map. Why?
Abstract (arXiv)
Time-series causal discovery methods rely on assumptions such as stationarity, regular sampling, and bounded temporal dependence. When these assumptions are violated, structure learning can produce confident but misleading causal graphs without warning. We introduce Causal-Audit, a framework that formalizes assumption validation as calibrated risk assessment. The framework computes effect-size diagnostics across five assumption families (stationarity, irregularity, persistence, nonlinearity, and confounding proxies), aggregates them into four calibrated risk scores with uncertainty intervals, and applies an abstention-aware decision policy that recommends methods (e.g., PCMCI+, VAR-based Granger causality) only when evidence supports reliable inference. The semi-automatic diagnostic stage can also be used independently for structured assumption auditing in individual studies. Evaluation on a synthetic atlas of 500 data-generating processes (DGPs) spanning 10 violation families demonstrates well-calibrated risk scores (AUROC > 0.95), a 62% false positive reduction among recommended datasets, and 78% abstention on severe-violation cases. On 21 external evaluations from TimeGraph (18 categories) and CausalTime (3 domains), recommend-or-abstain decisions are consistent with benchmark specifications in all cases. An open-source implementation of our framework is available.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 81 references that are in the map. First posted on arXiv 2 Apr 2026.
Builds on
26 of 81 references.
References · 26
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2017Selective Classification for Deep Neural Networkscited by 799
- 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
- 2017Detecting causal associations in large nonlinear time series datasetscited by 240
- 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
- 2020DYNOTEARS: Structure Learning from Time-Series Datacited by 198
- 2013Learning Bayesian Networks: The Combination of Knowledge and Statistical Datacited by 185
- 2019Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changescited by 166
- 2020Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasetscited by 136
- 2023Causal-learn: Causal Discovery in Pythoncited by 108
14 more
- 2017Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competitioncited by 106
- 2020High-recall causal discovery for autocorrelated time series with latent confounderscited by 82
- 2021Granger Causality: A Review and Recent Advancescited by 62
- 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
- 2023Scalable Causal Discovery with Score Matchingcited by 42
- 2023CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discoverycited by 35
- 2023Assumption violations in causal discovery and the robustness of score matchingcited by 28
- 2021Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Datacited by 22
- 2023Classifier Calibration with ROC-Regularized Isotonic Regressioncited by 19
- 2017Causal Inference: A Missing Data Perspectivecited by 14
- 2025TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discoverycited by 9
- 2023Bootstrap aggregation and confidence measures to improve time series causal discoverycited by 8
- 2025The Robustness of Differentiable Causal Discovery in Misspecified Scenarioscited by 4
- 2013Partial Transfer Entropy on Rank Vectorscited by 1
Built on by
Not cited yet.