{
  "apiVersion": "v1",
  "methodology": "https://sourcescore.org/methodology/",
  "canonical": "https://sourcescore.org/claims/927b56032c69c6e5/",
  "claim": {
    "vertical": "ai-ml",
    "subject": "Mask R-CNN",
    "predicate": "introduced_in_paper",
    "object": "Mask R-CNN (He et al., 2017)",
    "confidence": 0.82,
    "sources": [
      {
        "url": "https://arxiv.org/abs/1703.06870",
        "title": "Mask R-CNN",
        "publisher": "arXiv (Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick)",
        "publishedDate": "2017-03-20",
        "accessedDate": "2026-06-02",
        "type": "preprint",
        "excerpt": "Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition."
      },
      {
        "url": "https://huggingface.co/papers/1703.06870",
        "title": "Mask R-CNN (Hugging Face Papers)",
        "publisher": "Hugging Face",
        "accessedDate": "2026-06-02",
        "type": "docs"
      }
    ],
    "publishedAt": "2026-06-02T00:00:00Z",
    "lastVerified": "2026-06-02",
    "methodologyVersion": "veritas-v0.1",
    "tags": [
      "mask-rcnn",
      "instance-segmentation",
      "object-detection",
      "he",
      "girshick",
      "foundational",
      "2017"
    ],
    "id": "927b56032c69c6e5",
    "statement": "Mask R-CNN introduced in paper: Mask R-CNN (He et al., 2017)."
  },
  "signature": {
    "algorithm": "HMAC-SHA256",
    "signedBy": "did:web:sourcescore.org",
    "signedAt": "2026-06-02T00:00:00.000Z",
    "signature": "ce1e340f590611413657bdd125284000aa87d79feb92304d891c4ea4e2eceadf"
  },
  "citedAs": "Mask R-CNN introduced in paper: Mask R-CNN (He et al., 2017). — SourceScore Claim 927b56032c69c6e5 (verified 2026-06-02, signed ce1e340f…). https://sourcescore.org/claims/927b56032c69c6e5/"
}