Stress-Testing Causal Claims via Cardinality Repairs
Summary: SubCure stress-tests observational causal claims by solving cardinality-repair problems: find minimum tuple/pattern deletions that move an estimated effect into a target range. Shows even small data errors can flip causal conclusions; NP-complete formulations, then scalable incremental/unlearning-based auditing. (summarized by gpt-5.4-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yarden Gabbay (Technion)
- 2. Haoquan Guan (University of California San Diego)
- 3. Shaull Almagor (Technion)
- 4. El Kindi Rezig (University of Utah)
- 5. Brit Youngmann (Technion)
- 6. Babak Salimi (University of California San Diego)
BibTeX Citation
@inproceedings{gabbay_sigmod26,
title = {{Stress-Testing Causal Claims via Cardinality Repairs}},
author = {Gabbay, Yarden and Guan, Haoquan and Almagor, Shaull and Rezig, El Kindi and Youngmann, Brit and Salimi, Babak},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786700},
url = {https://dl.acm.org/doi/10.1145/3786700},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,991 | SubCure: A System for Stress-Testing Causal Conclusions Using Cardinality Repairs | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 24 of 24 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,229 | Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables | 2025 | SIGMOD |
| 2 | 406 | Deep Unsupervised Cardinality Estimation | 2020 | VLDB |
| 3 | 652 | Don’t be SCAREd: Use SCalable Automatic REpairing with Maximal Likelihood and Bounded Changes | 2013 | SIGMOD |
| 4 | 10,570 | From Suspicious Errors to Valid Data: On Repairing Spatio-Temporal Data via Spatial and Temporal Dependencies | 2026 | SIGMOD |
| 5 | 9,231 | Causal DAG Summarization | 2025 | VLDB |
| 6 | 2,964 | Towards Dependable Data Repairing with Fixing Rules | 2014 | SIGMOD |
| 7 | 6,771 | Causal Feature Selection for Algorithmic Fairness | 2022 | SIGMOD |
| 8 | 2,315 | Causal Relational Learning | 2020 | SIGMOD |
| 9 | 9,004 | The Cost of Representation by Subset Repairs | 2025 | VLDB |
| 10 | 10,991 | SubCure: A System for Stress-Testing Causal Conclusions Using Cardinality Repairs | 2026 | VLDB |