Generating Interpretable Data-Based Explanations for Fairness Debugging using Gopher

Summary: Gopher generates compact, interpretable, causal explanations for ML fairness by identifying the top-k coherent training-data subsets that are root causes. It quantifies removal/updating effects on bias, outlines an end-to-end architecture, and provides open-source code and a demo. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6383
Venue: SIGMOD
Year: 2022
Pagerank: 4.8676312e-05
Overall Rank: 7,000 | 51.31%
DOI: 10.1145/3514221.3520170

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,428	CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets	2025	SIGMOD	4.1945683e-05
10,524	Understanding the Black Box: A Deep Empirical Dive into Shapley Value Approximations for Tabular Data	2025	SIGMOD	4.1945683e-05

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
1,867	Interpretable Data-Based Explanations for Fairness Debugging	2022	SIGMOD	0.00010272055
1,940	SliceLine: Fast, Linear-Algebra-based Slice Finding for ML Model Debugging	2021	SIGMOD	0.00010020173
2,923	Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals	2021	SIGMOD	7.8953538e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
7,046	Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification	2022	SIGMOD	4.8525913e-05
13,256	DENOUNCER: Detection of Unfairness in Classifiers	2021	VLDB	-
10,428	CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets	2025	SIGMOD	4.1945683e-05
13,101	Interactive Fairness Auditing: Leveraging AVOIR for Dynamic Evaluation and Mitigation	2025	SIGMOD	-
4,935	OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning	2021	SIGMOD	5.8198727e-05
7,602	Causal Feature Selection for Algorithmic Fairness	2022	SIGMOD	4.6988081e-05
1,041	Interventional Fairness : Causal Database Repair for Algorithmic Fairness	2019	SIGMOD	0.00014482047
4,769	Automated Feature Engineering for Algorithmic Fairness	2021	VLDB	5.934329e-05
11,147	Reconstructing and Querying ML Pipeline Intermediates	2023	CIDR	4.1945683e-05
1,867	Interpretable Data-Based Explanations for Fairness Debugging	2022	SIGMOD	0.00010272055