{
 "id": "Amandeep10/pretrain-where-pretraining-datasets",
 "owner": "Amandeep10",
 "name": "pretrain-where-pretraining-datasets",
 "downloads": 2386,
 "likes": 1,
 "last_modified": "2026-05-25T18:10:41.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-feature-extraction"
 ],
 "citation": "Please cite the original paper when mentioning the datasets or our work.\n**BibTeX:**\n\n@misc{kaur2026pretrainwhereinvestigatingpretraining,\n      title={Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance}, \n      author={Amandeep Kaur and Mirali Purohit and Gedeon Muhawenayo and Esther Rolf and Hannah Kerner},\n      year={2026},\n      eprint={2604.21104},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2604.21104}, \n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "4ffdbf3634660549fbf3f4710e60409b1f8a2ca5",
 "stated_evidence": "https://huggingface.co/datasets/Amandeep10/pretrain-where-pretraining-datasets/blob/4ffdbf3634660549fbf3f4710e60409b1f8a2ca5/README.md",
 "file_evidence": "https://huggingface.co/datasets/Amandeep10/pretrain-where-pretraining-datasets/tree/4ffdbf3634660549fbf3f4710e60409b1f8a2ca5",
 "card_nc": false
}