Reproducibility Index

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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

International Conference on Learning Representations (ICLR) - 2015

Documentation Rate of Empirical Papers by Reproducibility Variable

Distribution of Empirical Papers by Number of Documented Variables

Website:

Venue Year Papers
Reproducibility Score Reproducibility Score based on Gundersen et al. (2025). See Methods for details.
Documentation Score Documentation Score is the average score over the seven reproducibility variables for empirical research papers. See Methods for details.
% 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 2015 31 0.53 3.5 96.77% 50.0%
Pseudocode
Open Source Code
Open Datasets
Dataset Splits
Hardware Specification
Software Dependencies
Experiment Setup
A Unified Perspective on Multi-Domain and Multi-Task Learning ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Adam: A Method for Stochastic Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Automatic Discovery and Optimization of Parts for Image Classification ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN) ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Deep Narrow Boltzmann Machines are Universal Approximators ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Deep Structured Output Learning for Unconstrained Text Recognition ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Embedding Entities and Relations for Learning and Inference in Knowledge Bases ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Explaining and Harnessing Adversarial Examples ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Fast Convolutional Nets With fbfft: A GPU Performance Evaluation ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
FitNets: Hints for Thin Deep Nets ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Generative Modeling of Convolutional Neural Networks ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Joint RNN-Based Greedy Parsing and Word Composition ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Leveraging Monolingual Data for Crosslingual Compositional Word Representations ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Memory Networks ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Modeling Compositionality with Multiplicative Recurrent Neural Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Move Evaluation in Go Using Deep Convolutional Neural Networks ❌ ❌ ❌ ✅ ✅ ❌ ✅ 3
Multiple Object Recognition with Visual Attention ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Neural Machine Translation by Jointly Learning to Align and Translate ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Object detectors emerge in Deep Scene CNNs ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Qualitatively characterizing neural network optimization problems ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Reweighted Wake-Sleep ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Scheduled denoising autoencoders ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition ❌ ❌ ✅ ❌ ❌ ✅ ✅ 3
Techniques for Learning Binary Stochastic Feedforward Neural Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
The local low-dimensionality of natural images ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Transformation Properties of Learned Visual Representations ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Understanding Locally Competitive Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Very Deep Convolutional Networks for Large-Scale Image Recognition ❌ ✅ ✅ ✅ ✅ ✅ ✅ 6
Word Representations via Gaussian Embedding ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Zero-bias autoencoders and the benefits of co-adapting features ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4