Verified claim · AI-ML · 100% confidence
CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021).
Last verified 2026-05-16 · Methodology veritas-v0.1 · bcdef949cc6d3644
Structured fields
- Subject
- CLIP
- Predicate
introduced_in_paper- Object
- Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021)
- Confidence
- 100%
- Tags
- clip · vision-language · multimodal · foundational · 2021 · openai
Sources (2)
[1] preprint · arXiv (Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, Sutskever) · 2021-02-26
Learning Transferable Visual Models From Natural Language Supervision“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.”
[2] official blog · OpenAI · 2021-01-05
CLIP: Connecting Text and Images
Cite this claim
Ready-to-paste citation (Markdown / plain text):
CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021). — SourceScore Claim bcdef949cc6d3644 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/bcdef949cc6d3644.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/bcdef949cc6d3644/" width="100%" height="360" frameborder="0" loading="lazy" title="CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021)."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
CLIP (Contrastive Language-Image Pretraining) introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021).
85a3ca745eaf4ee0 · 100% confidence · shares 4 tags (clip, multimodal, 2021…)
Codex introduced in paper: Evaluating Large Language Models Trained on Code (Chen et al., 2021).
79be9b25cd64f250 · 100% confidence · shares 3 tags (openai, foundational, 2021)
Low-Rank Adaptation (LoRA) introduced in paper: LoRA: Low-Rank Adaptation of Large Language Models (Hu et al., 2021).
d7b97d1b93d8d8bc · 100% confidence · shares 2 tags (foundational, 2021)
GPT-4o released on: 2024-05-13.
bd065b91ca6e880b · 100% confidence · shares 2 tags (openai, multimodal)
GPT-2 introduced in paper: Language Models are Unsupervised Multitask Learners (Radford et al., 2019).
859551dc078c46f8 · 100% confidence · shares 2 tags (foundational, openai)
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/bcdef949cc6d3644.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/bcdef949cc6d3644.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021)."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/bcdef949cc6d3644.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "CLIP introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021)."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_clip_fact() -> dict:
"""Fetch the verified SourceScore claim for CLIP."""
r = httpx.get("https://sourcescore.org/api/v1/claims/bcdef949cc6d3644.json")
return r.json()