{
 "id": "lance-format/dpr-wikipedia-single-nq",
 "owner": "lance-format",
 "name": "dpr-wikipedia-single-nq",
 "downloads": 307,
 "likes": 0,
 "last_modified": "2026-09-21T17:13:45.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-nc-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "The passage embeddings are the original [Facebook Research DPR](https://github.com/facebookresearch/DPR) single-NQ Wikipedia embeddings, downloaded in shard order 0 through 49 from `https://dl.fbaipublicfiles.com/dpr/data/wiki_encoded/single/nq/wiki_passages_{shard}`. `provenance.json` records source URLs and checksums.\n\nQueries use the official 3,610-question NQ test split, encoded with [`facebook/dpr-question_encoder-single-nq-base`](https://huggingface.co/facebook/dpr-question_encoder-single-nq-base) at revision `d04a52f6d2f96c60117a925e8c24c4043a75f265`, in evaluation mode, with maximum token length 256 and no vector normalization. Curly apostrophes in questions were replaced with ASCII apostrophes and surrounding whitespace was stripped.\n\nGround truth was computed against the complete corpus using exhaustive float32 dot products to retain the best 128 candidates, followed by float64 rescoring and sorting of those candidates to publish the top 100. The `scores` column contains these **float64 inner products**, where higher is better. A 16-query audit against exhaustive float64 search was performed during benchmark preparation; this is not a claim that every query was exhaustively scored in float64. Six queries have exact ties at the top-10 boundary.\n\n`passage_ids.lance` maps each `row_position` (uint64) to its original `passage_id`. The source shard order is preserved; passage IDs must not be substituted directly for ground-truth row positions.\n\nThe upstream DPR data is d",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "d95c3715333a608fa5eb8ca6fe8e6bdb724f32bd",
 "stated_evidence": "https://huggingface.co/datasets/lance-format/dpr-wikipedia-single-nq/blob/d95c3715333a608fa5eb8ca6fe8e6bdb724f32bd/README.md",
 "file_evidence": "https://huggingface.co/datasets/lance-format/dpr-wikipedia-single-nq/blob/d95c3715333a608fa5eb8ca6fe8e6bdb724f32bd/LICENSE",
 "card_nc": false
}