Article

Runtime Monitoring of Static Fairness Properties

2025-12-01

Abstract excerpt

<title>Abstract</title> <p>Machine-learned systems are in widespread use for making decisions about humans, and it is important that they are fair, i.e., not biased against individuals based on sensitive attributes. We present a general framework of runtime verification of algorithmic fairness for systems whose models are unknown, but are assumed to have a Markov chain structure, with or without full observation...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: d3a27704-f0f1-58ac-bb86-e54041c48e6d
DOI: 10.21203/rs.3.rs-7074584/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Runtime Monitoring of Static Fairness PropertiesDOI 10.21203/rs.3.rs-7074584/v1Read

Protocol-Dependent Resolution in Finite-Sample Model SelectionSemantic proximity Read

Confusions about race: a new installment.Semantic proximity Read

Humanizing the ATS-Based Recruiting Process by Using LLMs and Putting the Human Back in the LoopSemantic proximity Read

Consensus among Learning Agents: A Multi-AgentReinforcement Learning Framework withGame-Theoretic IncentivesSemantic proximity Read

Screening Feedback for Language Models with Costly VerificationSemantic proximity Read

The Game of Peers: Toward a Credential Algebra for Human-AI Actor NetworksSemantic proximity Read

Governing AI-Driven Prior Authorization:The Economic Case for Symbolic VerificationUnder CMS-0057-FSemantic proximity Read

Training as Treatment: A Causal Framework for Machine-Learning EvaluationSemantic proximity Read

Regret Is Weighted ForgettingSemantic proximity Read

K-Lean: Machine-Verified Formal Proofs for Computational BiologySemantic proximity Read

Polynomial-Time Exact Relabeling Fragility Analysis for Empirical Additive Treatment-by-Modifier InteractionsSemantic proximity Read

Characterizing human random-sequence generation in competitive and non-competitive environments using Lempel-Ziv complexitySemantic proximity Read