SourceScore

Verified claim · AI-ML · 100% confidence

ELECTRA introduced in paper: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (Clark et al., 2020).

Last verified 2026-05-16 · Methodology veritas-v0.1 · 2f9c79357e9d4da9

Structured fields

Subject
ELECTRA
Predicate
introduced_in_paper
Object
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (Clark et al., 2020)
Confidence
100%
Tags
electra · pretraining · discriminator · foundational · 2020 · google

Sources (2)

  1. [1] preprint · arXiv (Clark, Luong, Le, Manning) · 2020-03-23

    ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
    We propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network.
  2. [2] github release · Google Research · 2020-03-23

    google-research/electra — official implementation

Cite this claim

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

ELECTRA introduced in paper: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (Clark et al., 2020). — SourceScore Claim 2f9c79357e9d4da9 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/2f9c79357e9d4da9.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/2f9c79357e9d4da9/" width="100%" height="360" frameborder="0" loading="lazy" title="ELECTRA introduced in paper: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (Clark et al., 2020)."></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/2f9c79357e9d4da9.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/2f9c79357e9d4da9.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "ELECTRA introduced in paper: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (Clark et al., 2020)."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/2f9c79357e9d4da9.json") envelope = r.json() print(envelope["claim"]["statement"]) # "ELECTRA introduced in paper: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (Clark et al., 2020)."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_electra_fact() -> dict: """Fetch the verified SourceScore claim for ELECTRA.""" r = httpx.get("https://sourcescore.org/api/v1/claims/2f9c79357e9d4da9.json") return r.json()