Learning with Noisy Labels [~Re]visited
A replication report on learning from labels that contain errors, with source metadata identifying a Python deep-learning implementation.
External publication. Published by its original venue; not published in our journal.
How does a prespecified label-corruption schedule affect held-out accuracy and calibration across fixed seeds?
An evaluator controls corruption masks, test labels, scoring code and seed allocation; source output cannot define its own success.
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
Hudovernik, Valter; Rot, Žiga; Vovk, Klemen; Škodnik, Luka; Zajc, Luka Čehovin. Learning with Noisy Labels [~Re]visited. ReScience C 11(1), #2; 10.5281/zenodo.18401497.
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.
manuscript · CC-BY-4.0
The exact Zenodo record cited by the journal declares cc-by-4.0; the journal separately identifies published manuscripts as CC BY. This records manuscript rights, not separate code/data licenses or archive contents.
Inspect the license evidence ↗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.