CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets
Summary: Demo of CausalExplain, a model-agnostic system tracing ML predictions to training-data subsets via causal DAGs. It outputs top-k data-centric explanations from training-data predicates that causally drive the prediction, aiding debugging and insight across datasets and models. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Arman Ashkari (University of Utah)
- 2. El Kindi Rezig (University of Utah)
BibTeX Citation
@inproceedings{ashkari_sigmod25,
title = {{CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets}},
author = {Ashkari, Arman and Rezig, El Kindi},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3725087},
url = {https://dl.acm.org/doi/10.1145/3722212.3725087},
year = {2025}
}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 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,000 | Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals | 2021 | SIGMOD | 7.8677069e-05 |
| 7,068 | DataPrism: Exposing Disconnect between Data and Systems | 2022 | SIGMOD | 5.7119157e-05 |
| 7,192 | Generating Interpretable Data-Based Explanations for Fairness Debugging using Gopher | 2022 | SIGMOD | 5.6772818e-05 |
| 7,907 | Provenance-Enabled Explainable AI | 2024 | SIGMOD | 5.5181056e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,907 | Provenance-Enabled Explainable AI | 2024 | SIGMOD |
| 2 | 5,054 | Explainable AI: Foundations, Applications, Opportunities for Data Management Research | 2022 | SIGMOD |
| 3 | 1,951 | Interpretable Data-Based Explanations for Fairness Debugging | 2022 | SIGMOD |
| 4 | 10,710 | CauSumX: Summarized Causal Explanations For Group-By-Average Queries | 2025 | SIGMOD |
| 5 | 10,958 | What If: Causal Analysis with Graph Databases | 2025 | VLDB |
| 6 | 10,708 | CausaLens: A System for Summarizing Causal DAGs | 2025 | SIGMOD |
| 7 | 6,576 | Toward Interpretable and Actionable Data Analysis with Explanations and Causality | 2022 | VLDB |
| 8 | 13,462 | Demonstration of Generating Explanations for Black-Box Algorithms Using Lewis | 2021 | VLDB |
| 9 | 1,943 | Causality and Explanations in Databases | 2014 | VLDB |
| 10 | 3,000 | Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals | 2021 | SIGMOD |