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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
Adaptive Neural Trees
Authors: Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, Aditya Nori
ICML 2019 | Venue PDF | LLM Run Details | Input Tokens: 19,785 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,573 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically validate these benefits for regression and classification through experiments on the SARCOS (Vijayakumar & Schaal, 2000), MNIST (Le Cun et al., 1998) and CIFAR-10 (Krizhevsky & Hinton, 2009) datasets. |
| Researcher Affiliation | Collaboration | 1University College London, UK 2Imperial College London, UK 3Microsoft Research, Cambridge, UK. |
| Pseudocode | Yes | We include a pseudocode of the training algorithm in Supp. Sec. A. |
| Open Source Code | Yes | Codes: https://github.com/rtanno21609/Adaptive Neural Trees |
| Open Datasets | Yes | We evaluate ANTs using the SARCOS multivariate regression dataset (Vijayakumar & Schaal, 2000), and the MNIST (Le Cun et al., 1998) and CIFAR-10 (Krizhevsky & Hinton, 2009) classification datasets. |
| Dataset Splits | Yes | The best model is picked based on the performance on the same validation set of 5k examples as before. |
| Hardware Specification | No | Full training details, including training times on a single GPU, are provided in Supp. Sec. C and D. |
| Software Dependencies | No | All of our models are implemented in Py Torch (Paszke et al., 2017)1. |
| Experiment Setup | No | Full training details, including training times on a single GPU, are provided in Supp. Sec. C and D. |