reproducibilityindex.ai

International Conference on Learning Representations (ICLR)

Venue URL:

The Percentage of Empirical Papers Documenting Each Reproducibility Variable

Venue Year Papers
Repro. Score Reproducibility Score based on Gundersen et al. (2025)
Doc. Mean Global mean is the average score over the seven reproducibility variables for empirical research papers.
Doc. Median Global median is the median score over the seven reproducibility variables for empirical research papers.
Dataset Doc. Documentation mean is the average score over the Open Datasets and Dataset Splits reproducibility variables for empirical research papers.
Code Doc. Documentation mean is the average score over the Open Source Code reproducibility variables for empirical research papers.
Other Doc. Documentation mean is the average score over the Pseudocode, Hardware Specification, Software Dependencies, and Experiment Setup reproducibility variables for empirical research papers.
% Empirical Percentage of papers that are empirical research vs theoretical research
% Industry Percentage of empirical research papers with at least one author from Industry
Website
ICLR 2025 3700 0.66 4.54 5.0 1.59 0.69 2.26 97.97% 42.65%
ICLR 2024 2260 0.66 4.27 4.0 1.39 0.7 2.18 97.43% 48.86%
ICLR 2023 1573 0.66 4.29 4.0 1.46 0.7 2.13 96.82% 51.48%
ICLR 2022 1094 0.66 4.3 4.0 1.46 0.7 2.15 97.62% 50.94%
ICLR 2021 859 0.6 4.04 4.0 1.49 0.6 1.95 98.02% 51.43%
ICLR 2020 687 0.56 3.79 4.0 1.42 0.52 1.85 97.67% 55.89%
ICLR 2019 502 0.53 3.55 4.0 1.36 0.47 1.71 98.8% 54.44%
ICLR 2018 337 0.5 3.47 3.0 1.35 0.44 1.68 98.52% 56.93%
ICLR 2017 245 0.47 3.39 3.0 1.42 0.38 1.59 98.78% 51.65%
ICLR 2016 80 0.43 3.33 3.0 1.46 0.27 1.6 97.5% 51.28%
ICLR 2015 31 0.53 3.5 3.0 1.53 0.4 1.57 96.77% 50.0%
ICLR 2014 38 0.39 3.16 3.0 1.41 0.19 1.57 97.37% 27.03%