{
 "id": "lightonai/multilingual-embeddings-pre-training-curated",
 "owner": "lightonai",
 "name": "multilingual-embeddings-pre-training-curated",
 "downloads": 17351,
 "likes": 5,
 "last_modified": "2026-07-30T10:24:07.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@misc{sourty2026denseonlateonfullyopen,\n  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},\n  author        = {Rapha\u00ebl Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Am\u00e9lie Chatelain},\n  year          = {2026},\n  eprint        = {2607.27178},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.CL},\n  url           = {https://arxiv.org/abs/2607.27178},\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}