# Algorithmic Fairness: A Runtime Perspective

arXiv: https://arxiv.org/abs/2507.20711 · HTML: https://mlsanity.com/paper/2507.20711/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [Time-uniform, nonparametric, nonasymptotic confidence sequences](https://mlsanity.com/paper/1810.08240/) (2018)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [Delayed Impact of Fair Machine Learning](https://mlsanity.com/paper/1803.04383/) (2018)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning](https://mlsanity.com/paper/1903.01209/) (2019)
- [Verifying Individual Fairness in Machine Learning Models](https://mlsanity.com/paper/2006.11737/) (2020)
- [Average Individual Fairness: Algorithms, Generalization and Experiments](https://mlsanity.com/paper/1905.10607/) (2019)
- [Probabilistic Verification of Fairness Properties via Concentration](https://mlsanity.com/paper/1812.02573/) (2018)
- [Fair Normalizing Flows](https://mlsanity.com/paper/2106.05937/) (2021)
- [Justicia: A Stochastic SAT Approach to Formally Verify Fairness](https://mlsanity.com/paper/2009.06516/) (2020)
- [Certifying Robustness to Programmable Data Bias in Decision Trees](https://mlsanity.com/paper/2110.04363/) (2021)
- [Fairness-Aware PAC Learning from Corrupted Data](https://mlsanity.com/paper/2102.06004/) (2021)
- [Probabilistic Verification of Neural Networks Against Group Fairness](https://mlsanity.com/paper/2107.08362/) (2021)
- [Runtime Monitoring of Dynamic Fairness Properties](https://mlsanity.com/paper/2305.04699/) (2023)
- [Algorithmic Fairness Verification with Graphical Models](https://mlsanity.com/paper/2109.09447/) (2021)
- [Real-time Stream-based Monitoring](https://mlsanity.com/paper/1711.03829/) (2017)
- [Monitoring Algorithmic Fairness](https://mlsanity.com/paper/2305.15979/) (2023)
- [Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making](https://mlsanity.com/paper/2312.04772/) (2023)
- [Monitoring Algorithmic Fairness under Partial Observations](https://mlsanity.com/paper/2308.00341/) (2023)
- [Fairness Shields: Safeguarding against Biased Decision Makers](https://mlsanity.com/paper/2412.11994/) (2024)

## Abstract (arXiv)

Fairness in AI is traditionally studied as a static property evaluated once, over a fixed dataset. However, real-world AI systems operate sequentially, with outcomes and environments evolving over time. This paper proposes a framework for analysing fairness as a runtime property. Using a minimal yet expressive model based on sequences of coin tosses with possibly evolving biases, we study the problems of monitoring and enforcing fairness expressed in either toss outcomes or coin biases. Since there is no one-size-fits-all solution for either problem, we provide a summary of monitoring and enforcement strategies, parametrised by environment dynamics, prediction horizon, and confidence thresholds. For both problems, we present general results under simple or minimal assumptions. We survey existing solutions for the monitoring problem for Markovian and additive dynamics, and existing solutions for the enforcement problem in static settings with known dynamics.