Provenance-Enabled Explainable AI
Summary: PXAI decouples XAI from ML models via a provenance graph that tracks data creation and transformation throughout the model. Prunes irrelevant variables and computations to accelerate explanations; case studies show efficiency gains for complex models. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jiachi Zhang (Alibaba)
- 2. Wenchao Zhou (Alibaba)
- 3. Benjamin E. Ujcich (Georgetown University)
BibTeX Citation
@inproceedings{zhang_sigmod24,
title = {{Provenance-Enabled Explainable AI}},
author = {Zhang, Jiachi and Zhou, Wenchao and Ujcich, Benjamin E.},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3698826},
url = {https://dl.acm.org/doi/10.1145/3698826},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,151 | CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets | 2025 | SIGMOD | 4.9769913e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 17 | Provenance Semirings | 2007 | PODS | 0.00059813669 |
| 1,568 | HELIX: Holistic Optimization for Accelerating Iterative Machine Learning | 2019 | VLDB | 0.00010208225 |
| 1,611 | Efficient Provenance Storage | 2008 | SIGMOD | 0.00010072076 |
| 1,785 | Approximate Lineage for Probabilistic Databases | 2008 | VLDB | 9.6438009e-05 |
| 2,447 | noWorkflow: a Tool for Collecting, Analyzing, and Managing Provenance from Python Scripts | 2017 | VLDB | 8.4530494e-05 |
| 4,197 | PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models | 2020 | SIGMOD | 6.7390419e-05 |
| 4,334 | LIMA: Fine-grained Lineage Tracing and Reuse in Machine Learning Systems | 2021 | SIGMOD | 6.6537801e-05 |
| 6,193 | Fine-Grained Lineage for Safer Notebook Interactions | 2021 | VLDB | 5.8538103e-05 |
| 6,712 | Selective Provenance for Datalog Programs Using Top-K Queries | 2015 | VLDB | 5.70009e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,851 | Bolt-on, Verifiable Provenance for LLM-Powered Data Processing | 2026 | VLDB |
| 2 | 6,488 | Approximate Summaries for Why and Why-not Provenance | 2020 | VLDB |
| 3 | 11,151 | CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets | 2025 | SIGMOD |
| 4 | 7,214 | Capturing and Querying Fine-grained Provenance of Preprocessing Pipelines in Data Science | 2021 | VLDB |
| 5 | 621 | On the Provenance of Non-Answers to Queries over Extracted Data | 2008 | VLDB |
| 6 | 4,684 | Provenance for Natural Language Queries | 2017 | VLDB |
| 7 | 13,781 | Demonstration of Generating Explanations for Black-Box Algorithms Using Lewis | 2021 | VLDB |
| 8 | 5,179 | Explainable AI: Foundations, Applications, Opportunities for Data Management Research | 2022 | SIGMOD |
| 9 | 3,065 | Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals | 2021 | SIGMOD |
| 10 | 13,604 | PROXAI: Interactive Provenance-Aware Debugging of Machine Learning Pipelines | 2026 | VLDB |