Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

International Conference on Machine Learning (ICML)

Venue URL:

The Percentage of Empirical Papers Documenting Each Reproducibility Variable

Venue
Reproducibility Score based on Gundersen et al. (2025)
Global mean is the average score over the seven reproducibility variables for empirical research papers.
Percentage of papers that are empirical research vs theoretical research
Percentage of empirical research papers with at least one author from Industry
Website
ICML 2025 3330 0.61 4.42 94.95% 36.69%
ICML 2024 2610 0.62 4.11 93.03% 39.99%
ICML 2023 1828 0.6 4.06 91.47% 43.84%
ICML 2022 1233 0.58 3.97 92.94% 42.84%
ICML 2021 1183 0.52 3.38 92.98% 45.09%
ICML 2020 1084 0.52 3.43 90.68% 44.05%
ICML 2019 773 0.49 3.23 92.24% 46.28%
ICML 2018 621 0.42 3.13 94.52% 40.2%
ICML 2017 434 0.39 3.15 92.17% 41.25%
ICML 2016 322 0.36 3.07 93.17% 33.0%
ICML 2015 270 0.37 3.24 94.07% 28.35%
ICML 2014 310 0.3 3.0 93.55% 27.59%