{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicr3frmhpqnyzqbwezwvzum3l7wj73sektx6zj4li4kofr6zbuvxq",
    "uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mklmf6c6nmq2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreigexk2tegamgpnwbwuu7pboghcowdrzkhy7tqftt5xg6hisk2r6q4"
    },
    "mimeType": "image/jpeg",
    "size": 296747
  },
  "path": "/news/2026-04-ai-quantify-beauty.html",
  "publishedAt": "2026-04-28T17:00:04.000Z",
  "site": "https://techxplore.com",
  "tags": [
    "Computer Sciences"
  ],
  "textContent": "Attempts to define human beauty using artificial intelligence may reveal more about bias in data than universal standards, according to a new analysis from the University of Virginia's School of Data Science. Using computer vision and statistical modeling, researchers evaluated whether facial features align with the \"Golden Ratio,\" a mathematical formula often cited as an objective measure of attractiveness. Instead, the analysis found that demographic variation, not mathematical proportion, was the strongest factor shaping model outputs. This challenges long-standing assumptions that beauty can be quantified.",
  "title": "Can AI quantify beauty? New study suggests it can't"
}