FAIRsharing record for: Leakage and the Reproducibility Crisis in ML-based Science

FAIRsharing.org 2026 Dataset Open access

Read full text
Authors: FAIRsharing Team, Léa Girard
DOI: 10.25504/fairsharing.ea6373
Cited by: 0

Abstract

This FAIRsharing record describes: The document introduces a structured taxonomy of leakage types and recommends transparent reporting practices, including model info sheets, to improve reporting and reliability in ML-based science.

Fields of Study & Subjects

Scientific Computing and Data Management Research Data Management Practices Academic Publishing and Open Access

Publication details

Journal / source
FAIRsharing.org
Publication date
6 February 2026
Document type
Dataset