[Re] Learning Fair Graph Representations via Automated Data Augmentations

Does the performance–fairness tradeoff persist under held-out graph splits chosen before training?

Freeze graph splits, protected-group definitions and metric code independently, and report each metric rather than a single author success flag.

What you could produce

• Versioned protocol, input and environment manifest, and independent per-case comparison table including uncertainty and incomplete cases.

Before you use it

• Exact article-specific dependencies, data and build requirements remain uninspected.

Limits to keep in view

• No research code was executed; no independent scientific verification has been performed.
• The current qualified pilot is self-contained Python 3.13 with a 90-second author deadline. This article's environment has not been qualified for that path.
• Published source metadata and a historical review do not establish compatibility, successful reproduction, operator independence or current scientific correctness.

Source and permission context

Belitsky, Max; Laitenberger, Filipe; Sheremet, Denys; Belkacemi, Nordin. [Re] Learning Fair Graph Representations via Automated Data Augmentations. ReScience C 10(1), #6; 10.5281/zenodo.16374814.

Catalog listing reviewed. This review covers the description and source links displayed here.

ReScience/Zenodo metadata reviewed; exact CC-BY-4.0 evidence is manuscript-scoped.

Reviewed 2026-09-14. Copying or adapting source files remains subject to their own terms.

Before copying source material

• The associated code's exact license and version-specific third-party notices have not been independently checked.
• Data licenses, permissions, consent restrictions and redistribution conditions have not been independently checked.
• Artifacts are referenced only; PDF/archive contents, dependency locks and bytes have not been inspected or executed.