SourceScore

Verified claim · AI-ML · 100% confidence

Switch Transformer introduced in paper: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus et al., 2021).

Last verified 2026-05-16 · Methodology veritas-v0.1 · 3d9c14b9379038c9

Structured fields

Subject
Switch Transformer
Predicate
introduced_in_paper
Object
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus et al., 2021)
Confidence
100%
Tags
switch-transformer · moe · foundational · fedus · 2021 · google

Sources (2)

  1. [1] preprint · arXiv (Fedus, Zoph, Shazeer) · 2021-01-11

    Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
    We simplify the MoE routing algorithm and design intuitive improved models with reduced communication and computational costs.
  2. [2] peer reviewed · Journal of Machine Learning Research · 2022-12-01

    Switch Transformers (JMLR 2022)

Cite this claim

Ready-to-paste citation (Markdown / plain text):

Switch Transformer introduced in paper: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus et al., 2021). — SourceScore Claim 3d9c14b9379038c9 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/3d9c14b9379038c9.json

Embed 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/3d9c14b9379038c9/" width="100%" height="360" frameborder="0" loading="lazy" title="Switch Transformer introduced in paper: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus 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.

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/3d9c14b9379038c9.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/3d9c14b9379038c9.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "Switch Transformer introduced in paper: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus et al., 2021)."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/3d9c14b9379038c9.json") envelope = r.json() print(envelope["claim"]["statement"]) # "Switch Transformer introduced in paper: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus et al., 2021)."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_switch_transformer_fact() -> dict: """Fetch the verified SourceScore claim for Switch Transformer.""" r = httpx.get("https://sourcescore.org/api/v1/claims/3d9c14b9379038c9.json") return r.json()