---
title: "rstudio/keras3: papers citing this GitHub repository"
description: "9 papers in the tracked journals link to the GitHub repository rstudio/keras3 in their Crossref records, the first in 2021; most of them (3) in 2024."
url: https://scholar4ai.com/code/github-rstudio-keras3
markdown_url: https://scholar4ai.com/code/github-rstudio-keras3.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "9 papers in the tracked journals link to the GitHub repository rstudio/keras3 in their Crossref records, the first in 2021; most of them (3) in 2024. (as of 2026-11-03)"
data_url: https://scholar4ai.com/data/rankings.json
updated: 2026-11-03T14:43:26+09:00
window: 2026-10-05 to 2026-11-03
source: OpenAlex (CC0)
---

# rstudio/keras3: papers linking to it

Research papers in the 480 tracked journals that link to rstudio/keras3 (https://github.com/rstudio/keras3), read from their Crossref records: by year, category and journal, the family tree of papers building on one another, and the linked repositories derived from it or that it derives from.

- GitHub
- 857 stars
- 279 forks
- R
- created 2017
- https://github.com/rstudio/keras3

All repositories: https://scholar4ai.com/code.md

## Key findings

- 9 papers in the tracked journals link to the GitHub repository rstudio/keras3 in their Crossref records, the first in 2021; most of them (3) in 2024.
- By category: Finance (6), Statistics (2) and AI (1); the journals with the most are European Actuarial Journal (6), Journal of Statistical Theory and Practice (1) and Japanese Journal of Statistics and Data Science (1).
- 6 of the papers build on one another: a later paper cites an earlier one that also links rstudio/keras3.

## By year

*Papers linking to rstudio/keras3 by publication year*

| Year | Papers |
|---|---:|
| 2021 | 2 |
| 2022 | 2 |
| 2023 | 1 |
| 2024 | 3 |
| 2025 | 1 |

## Journals

*Journals whose papers link to rstudio/keras3 most*

| Journal | Papers |
|---|---:|
| [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | 6 |
| [Journal of Statistical Theory and Practice](https://scholar4ai.com/journals/journal-of-statistical-theory-and-practice.md) | 1 |
| [Japanese Journal of Statistics and Data Science](https://scholar4ai.com/journals/japanese-journal-of-statistics-and-data-science.md) | 1 |
| [Neural Computing and Applications](https://scholar4ai.com/journals/neural-computing-and-applications.md) | 1 |

## Family tree

Each paper sits under the earlier paper it builds on.

- [Efficient use of data for LSTM mortality forecasting](https://doi.org/10.1007/s13385-022-00307-3) (European Actuarial Journal, 2022)
  - [A neural network approach for the mortality analysis of multiple populations: a case study on data of the Italian population](https://doi.org/10.1007/s13385-024-00377-5) (European Actuarial Journal, 2024) — cites the paper above
- [Micro-level prediction of outstanding claim counts based on novel mixture models and neural networks](https://doi.org/10.1007/s13385-022-00314-4) (European Actuarial Journal, 2022)
  - [Combined modelling of micro-level outstanding claim counts and individual claim frequencies in non-life insurance](https://doi.org/10.1007/s13385-024-00383-7) (European Actuarial Journal, 2024) — cites the paper above
- [High-cardinality categorical covariates in network regressions](https://doi.org/10.1007/s42081-024-00243-4) (Japanese Journal of Statistics and Data Science, 2024)
  - [The credibility transformer](https://doi.org/10.1007/s13385-025-00413-y) (European Actuarial Journal, 2025) — cites the paper above

## Papers

*Papers linking to rstudio/keras3, most cited first*

| Published | Title | Journal | Authors | Citations | Link |
|---|---|---|---|---:|---|
| 2022-04-02 | [Efficient use of data for LSTM mortality forecasting](https://doi.org/10.1007/s13385-022-00307-3) | [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | Mathias Lindholm, Lina Palmborg | 31 | cites it |
| 2023-11-08 | [A multi-task network approach for calculating discrimination-free insurance prices](https://doi.org/10.1007/s13385-023-00367-z) | [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | Mathias Lindholm, Ronald Richman, Andreas Tsanakas et al. | 14 | cites it |
| 2021-01-29 | [Deep neural networks architecture driven by problem-specific information](https://doi.org/10.1007/s00521-021-05702-7) | [Neural Computing and Applications](https://scholar4ai.com/journals/neural-computing-and-applications.md) | Daniel Urda, Francisco J. Veredas, Javier González-Enrique et al. | 12 | cites it |
| 2022-05-12 | [Micro-level prediction of outstanding claim counts based on novel mixture models and neural networks](https://doi.org/10.1007/s13385-022-00314-4) | [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | Axel Bücher, Alexander Rosenstock | 12 | cites it |
| 2024-03-06 | [A neural network approach for the mortality analysis of multiple populations: a case study on data of the Italian population](https://doi.org/10.1007/s13385-024-00377-5) | [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | Maximilian Euthum, Matthias A. Scherer, Francesco Ungolo | 9 | cites it |
| 2025-02-15 | [The credibility transformer](https://doi.org/10.1007/s13385-025-00413-y) | [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | Ronald Richman, Salvatore Scognamiglio, Mario V. Wüthrich | 7 | cites it |
| 2024-02-25 | [High-cardinality categorical covariates in network regressions](https://doi.org/10.1007/s42081-024-00243-4) | [Japanese Journal of Statistics and Data Science](https://scholar4ai.com/journals/japanese-journal-of-statistics-and-data-science.md) | Ronald Richman, Mario V. Wüthrich | 5 | cites it |
| 2021-05-25 | [On Ensembles, I-Optimality, and Active Learning](https://doi.org/10.1007/s42519-021-00200-4) | [Journal of Statistical Theory and Practice](https://scholar4ai.com/journals/journal-of-statistical-theory-and-practice.md) | William D. Heavlin | 2 | cites it |
| 2024-04-24 | [Combined modelling of micro-level outstanding claim counts and individual claim frequencies in non-life insurance](https://doi.org/10.1007/s13385-024-00383-7) | [European Actuarial Journal](https://scholar4ai.com/journals/european-actuarial-journal.md) | Axel Bücher, Alexander Rosenstock | 0 | cites it |

## How this is measured

Links are read from each paper's Crossref record as its publisher deposited it: the URLs and repository DOIs in its reference list (the software and data it cites) and its supplementary links (“is-supplemented-by”: its own code or data). A paper that gives its code only in the text, a footnote or a data availability statement is not counted, and some publishers deposit reference lists without their URLs, so every count here is a lower bound. Repository details come from the GitHub REST API (stars, forks, and the repository a fork was made from), the Hugging Face Hub API (likes, downloads, and the base model a model was derived from) and DataCite (Zenodo and other data DOIs, and the GitHub release a Zenodo record archives), read again every month.

## Cite this page

Scholar4AI. (2026). rstudio/keras3: papers linking to it. Journal and Conference Research Rankings. Retrieved November 3, 2026, from https://scholar4ai.com/code/github-rstudio-keras3

```bibtex
@misc{scholar4ai-code-github-rstudio-keras3,
  author = {{Scholar4AI}},
  title = {rstudio/keras3: papers linking to it},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/code/github-rstudio-keras3}},
  urldate = {2026-11-03},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}
```

License: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/).