Code accompanying the paper "Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model"

DOI:10.4121/176f8fbe-8791-4f9d-9ab9-28a33c2685f1.v1

The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/176f8fbe-8791-4f9d-9ab9-28a33c2685f1

Datacite citation style

Zanger, Moritz A.; van der Vaart, Pascal; Boehmer, Wendelin; Spaan, M.T.J. (Matthijs) (2025): Code accompanying the paper "Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model". Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/176f8fbe-8791-4f9d-9ab9-28a33c2685f1.v1

Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite

Software

Keywords

data augmentation deep ensembles machine learning reinforcement learning Uncertainty quantification

Licence

MIT

Interoperability

RO-Crate Metadata

Export as...

RefWorks BibTeX Reference Manager Endnote DataCite NLM DC CFF

by Moritz A. Zanger

, Pascal van der Vaart

, Wendelin Boehmer, M.T.J. (Matthijs) Spaan

This is the official code repository accompanying the paper "Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model".

History

2025-08-18 first online, published, posted

Publisher

4TU.ResearchData

Format

.py

Associated peer-reviewed publication

References

https://arxiv.org/abs/2503.11339

Funding

Epistemic AI (grant code 964505) [more info...] EXCELLENT SCIENCE - Future and Emerging Technologies (FET) (EU Horizons 2020)

Organizations

Delft University of Technology, Faculty of Electrical Engineering, Mathematics and Computer Science,
Department of Intelligent Systems, Sequential Decision Making Group

DATA - under embargo

The files in this dataset are under embargo until 2027-08-14.

Reason

This dataset contains source code developed to reproduce experiments for an ongoing research project that has not yet been formally published. While a preprint version of the associated manuscript is publicly available, the code itself remains confidential to protect the integrity of the research and the publication process. Direct access to the code will be granted only in exceptional circumstances and will remain restricted until the official publication of the associated work.