{
  "id": "alpaca-cleaned",
  "name": "Alpaca-Cleaned",
  "identifiers": {
    "huggingface": [
      "yahma/alpaca-cleaned"
    ]
  },
  "builder": "gururise / yahma (community)",
  "release_date": {
    "value": "2023-03-24",
    "source": "https://huggingface.co/api/datasets/yahma/alpaca-cleaned",
    "status": "partial",
    "note": "HF dataset repo creation date, not the builder's own release announcement."
  },
  "availability": {
    "value": "available",
    "checked": "2026-09-24",
    "source": "https://huggingface.co/datasets/yahma/alpaca-cleaned"
  },
  "content": {
    "value": "Card: 'a cleaned version of the original Alpaca Dataset released by Stanford', fixing hallucinations, empty outputs and similar issues. Derivation from `alpaca-52k` is recorded in prose (no dataset-to-dataset edge). The card refers to the original outputs as GPT3's.",
    "source": "https://huggingface.co/datasets/yahma/alpaca-cleaned",
    "status": "recorded"
  },
  "primary_sources": [
    "https://huggingface.co/datasets/yahma/alpaca-cleaned",
    "https://github.com/gururise/AlpacaDataCleaned"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "created from primary sources (tranche 2 dataset records)",
      "by": "wilson-pruitt + claude"
    }
  ]
}