ExTuNe: Explaining Tuple Non-conformance
Summary: ExTuNe defines data invariants—implicit multi-attribute constraints that capture dataset conformance—and uses causal interventions to attribute non-conformance to specific attributes. It ranks test tuples by violation degree and visualizes attribute responsibility with heat maps to enable explanations and trusted ML. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Anna Fariha (University of Massachusetts Amherst)
- 2. Ashish Tiwari (Microsoft)
- 3. Arjun Radhakrishna (Microsoft)
- 4. Sumit Gulwani (Microsoft)
BibTeX Citation
@inproceedings{fariha_sigmod20,
title = {{ExTuNe: Explaining Tuple Non-conformance}},
author = {Fariha, Anna and Tiwari, Ashish and Radhakrishna, Arjun and Gulwani, Sumit},
series = {{SIGMOD} '20},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3318464.3384694},
url = {https://dl.acm.org/doi/10.1145/3318464.3384694},
year = {2020}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,397 | Conformance Constraint Discovery: Measuring Trust in Data-Driven Systems | 2021 | SIGMOD | 5.6256632e-05 |
| 7,749 | CoCo: Interactive Exploration of Conformance Constraints for Data Understanding and Data Cleaning | 2021 | SIGMOD | 5.5525665e-05 |
| 8,184 | FEDEX: An Explainability Framework for Data Exploration Steps | 2022 | VLDB | 5.4709725e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 191 | Scorpion: Explaining Away Outliers in Aggregate Queries | 2013 | VLDB | 0.00026096009 |
| 5,050 | CAPE: Explaining Outliers by Counterbalancing | 2019 | VLDB | 6.3862246e-05 |
| 5,268 | ANMAT: Automatic Knowledge Discovery and Error Detection through Pattern Functional Dependencies | 2019 | SIGMOD | 6.2923403e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,709 | CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets | 2025 | SIGMOD |
| 2 | 7,977 | Interactive Query Explanations Using Fine Grained Provenance | 2022 | SIGMOD |
| 3 | 4,140 | Interactive Mapping Specification with Exemplar Tuples | 2017 | SIGMOD |
| 4 | 11,660 | INCA: Inconsistency-Aware Data Profiling and Querying | 2021 | SIGMOD |
| 5 | 6,576 | Toward Interpretable and Actionable Data Analysis with Explanations and Causality | 2022 | VLDB |
| 6 | 11,479 | CM-Explorer: Dissecting Data Ingestion Problems | 2023 | VLDB |
| 7 | 11,424 | Splitting Tuples of Mismatched Entities | 2023 | SIGMOD |
| 8 | 628 | On the Provenance of Non-Answers to Queries over Extracted Data | 2008 | VLDB |
| 9 | 856 | How to ConQueR Why-Not Questions | 2010 | SIGMOD |
| 10 | 7,397 | Conformance Constraint Discovery: Measuring Trust in Data-Driven Systems | 2021 | SIGMOD |