{
  "apiVersion": "v1",
  "methodology": "https://sourcescore.org/methodology/",
  "canonical": "https://sourcescore.org/claims/bcdef949cc6d3644/",
  "claim": {
    "vertical": "ai-ml",
    "subject": "CLIP",
    "predicate": "introduced_in_paper",
    "object": "Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021)",
    "confidence": 1,
    "sources": [
      {
        "url": "https://arxiv.org/abs/2103.00020",
        "title": "Learning Transferable Visual Models From Natural Language Supervision",
        "publisher": "arXiv (Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, Sutskever)",
        "publishedDate": "2021-02-26",
        "accessedDate": "2026-05-16",
        "type": "preprint",
        "excerpt": "We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet."
      },
      {
        "url": "https://openai.com/research/clip",
        "title": "CLIP: Connecting Text and Images",
        "publisher": "OpenAI",
        "publishedDate": "2021-01-05",
        "accessedDate": "2026-05-16",
        "type": "official-blog"
      }
    ],
    "publishedAt": "2026-05-16T00:00:00Z",
    "lastVerified": "2026-05-16",
    "methodologyVersion": "veritas-v0.1",
    "tags": [
      "clip",
      "vision-language",
      "multimodal",
      "foundational",
      "2021",
      "openai"
    ],
    "id": "bcdef949cc6d3644",
    "statement": "CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021)."
  },
  "signature": {
    "algorithm": "HMAC-SHA256",
    "signedBy": "did:web:sourcescore.org",
    "signedAt": "2026-05-16T00:00:00.000Z",
    "signature": "6d86a6583a17281c64bf21ac707a7cd4f72ab3f11e89be171aea0859d64d2977"
  },
  "citedAs": "CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021). — SourceScore Claim bcdef949cc6d3644 (verified 2026-05-16, signed 6d86a658…). https://sourcescore.org/claims/bcdef949cc6d3644/"
}