Zorro: Quantifying Uncertainty in Models & Predictions Arising from Dirty Data
Summary: Zorro quantifies uncertainty from dirty data by considering all plausible clean datasets and their linear models. It over-approximates possible models and predictions to certify robustness of parameters and predictions against data quality issues. (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. Kaiyuan Hu (University of California San Diego)
- 2. Jiongli Zhu (University of California San Diego)
- 3. Boris Glavic (University of Illinois Chicago)
- 4. Babak Salimi (University of California San Diego)
BibTeX Citation
@inproceedings{hu_sigmod25,
title = {{Zorro: Quantifying Uncertainty in Models \& Predictions Arising from Dirty Data}},
author = {Hu, Kaiyuan and Zhu, Jiongli and Glavic, Boris and Salimi, Babak},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3725143},
url = {https://dl.acm.org/doi/10.1145/3722212.3725143},
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 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,351 | Detecting Data Errors: Where are we and what needs to be done? | 2016 | VLDB | 0.00011064851 |
| 2,147 | Nearest Neighbor Classifiers over Incomplete Information: From Certain Answers to Certain Predictions | 2021 | VLDB | 9.0831495e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,281 | Cleaning Crowdsourced Labels Using Oracles for Statistical Classification | 2019 | VLDB |
| 2 | 10,991 | Stress-Testing ML Pipelines with Adversarial Data Corruption | 2025 | VLDB |
| 3 | 9,206 | A Data Quality Metric (DQM): How to Estimate the Number of Undetected Errors in Data Sets | 2017 | VLDB |
| 4 | 9,204 | Selecting Data to Clean for Fact Checking: Minimizing Uncertainty vs. Maximizing Surprise | 2019 | VLDB |
| 5 | 10,604 | Fault Lines: Benchmarking the Impact of Label Data Quality on ML Robustness and Fairness | 2026 | VLDB |
| 6 | 112 | HoloClean: Holistic Data Repairs with Probabilistic Inference | 2017 | VLDB |
| 7 | 9,193 | Query-Guided Resolution in Uncertain Databases | 2023 | SIGMOD |
| 8 | 7,880 | Learning Over Dirty Data Without Cleaning | 2020 | SIGMOD |
| 9 | 11,343 | Generalizable Data Cleaning of Tabular Data in Latent Space | 2024 | VLDB |
| 10 | 1,323 | Data Cleaning: Overview and Emerging Challenges | 2016 | SIGMOD |