ShapGraph: An Holistic View of Explanations through Provenance Graphs and Shapley Values
Summary: ShapGraph blends provenance graphs (global explanations) with Shapley-value-based tuple contributions (local explanations) for query results. An interactive GUI lets researchers switch between and combine views to identify influential data and how they interact to drive answers. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Susan Davidson (University of Pennsylvania)
- 2. Daniel Deutch (Tel Aviv University)
- 3. Nave Frost (eBay)
- 4. Benny Kimelfeld (Technion 6 Israel Institute of Technology)
- 5. Omer Koren (Tel Aviv University)
- 6. Mikael Monet (CNRS; Centrale Lille; INRIA; University of Lille)
BibTeX Citation
@inproceedings{davidson_sigmod22,
title = {{ShapGraph: An Holistic View of Explanations through Provenance Graphs and Shapley Values}},
author = {Davidson, Susan and Deutch, Daniel and Frost, Nave and Kimelfeld, Benny and Koren, Omer and Monet, Mikael},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3520172},
url = {https://dl.acm.org/doi/10.1145/3514221.3520172},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,918 | From Shapley Value to Model Counting and Back | 2024 | PODS | 7.0181891e-05 |
| 5,660 | Banzhaf Values for Facts in Query Answering | 2024 | SIGMOD | 6.1305635e-05 |
| 9,541 | Shapley Value Estimation Based on Differential Matrix | 2025 | SIGMOD | 5.2528121e-05 |
| 10,198 | ASSS: Adaptive Stratified Sampling for Shapley-like Values | 2026 | SIGMOD | 5.093636e-05 |
| 10,214 | CoShap: A Scalable Coalition Growth Approach to Shapley Value Approximation | 2026 | SIGMOD | 5.093636e-05 |
| 10,679 | SHARQ: Explainability Framework for Association Rules on Relational Data | 2025 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 385 | Why Not? | 2009 | SIGMOD | 0.00019455743 |
| 605 | The Complexity of Causality and Responsibility for Query Answers and non-Answers | 2011 | VLDB | 0.00015839628 |
| 1,912 | Querying Data Provenance | 2010 | SIGMOD | 9.4946756e-05 |
| 1,965 | ProvSQL: Provenance and Probability Management in PostgreSQL | 2018 | VLDB | 9.3852716e-05 |
| 2,424 | Computing the Shapley Value of Facts in Query Answering | 2022 | SIGMOD | 8.6009068e-05 |
| 2,503 | The Semiring Framework for Database Provenance | 2017 | PODS | 8.4964654e-05 |
| 2,670 | The Impact of Negation on the Complexity of the Shapley Value in Conjunctive Queries | 2020 | PODS | 8.2737143e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,461 | Explain3D: Explaining Disagreements in Disjoint Datasets | 2019 | VLDB |
| 2 | 10,183 | Tractability Frontiers of the Shapley Value for Aggregate Conjunctive Queries | 2026 | PODS |
| 3 | 10,906 | A Comprehensive Study of Shapley Value in Data Analytics | 2025 | VLDB |
| 4 | 7,977 | Interactive Query Explanations Using Fine Grained Provenance | 2022 | SIGMOD |
| 5 | 10,679 | SHARQ: Explainability Framework for Association Rules on Relational Data | 2025 | SIGMOD |
| 6 | 9,809 | Shapley Revisited: Tractable Responsibility Measures for Query Answers | 2025 | PODS |
| 7 | 5,382 | Expected Shapley-Like Scores of Boolean Functions: Complexity and Applications to Probabilistic Databases | 2024 | PODS |
| 8 | 10,043 | SHARQL: Shape Analysis of Recursive SPARQL Queries | 2020 | SIGMOD |
| 9 | 5,396 | Putting Things into Context: Rich Explanations for Query Answers using Join Graphs | 2021 | SIGMOD |
| 10 | 2,424 | Computing the Shapley Value of Facts in Query Answering | 2022 | SIGMOD |