Verified claim · AI-ML · 100% confidence
CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 326d6dd16bd353d1
Structured fields
- Subject
- CRAG (Corrective RAG)
- Predicate
introduced_in- Object
- Yan et al. 2024 — corrective retrieval-augmented generation
- Confidence
- 100%
- Tags
- crag · corrective-rag · ustc · google · rag · foundational · 2024 · introduced_in
Sources (2)
[1] preprint · arXiv (Yan, Gan, Mao, Zhu, Wu, Xu, Liu, Liu / USTC + Google) · 2024-01-29
Corrective Retrieval Augmented Generation“We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. Specifically, a lightweight retrieval evaluator is designed to assess the overall quality of retrieved documents for a query, returning a confidence degree.”
[2] github release · USTC team · 2024-01-29
CRAG — official reference implementation
Cite this claim
Ready-to-paste citation (Markdown / plain text):
CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation. — SourceScore Claim 326d6dd16bd353d1 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/326d6dd16bd353d1.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/326d6dd16bd353d1/" width="100%" height="360" frameborder="0" loading="lazy" title="CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
GraphRAG introduced in: Edge et al. 2024 — Microsoft Research knowledge-graph RAG.
58a9c41f05c73a22 · 100% confidence · shares 4 tags (rag, foundational, 2024…)
Knowledge Distillation popularized in: Hinton, Vinyals, Dean 2015 — distilling the knowledge in a neural network.
f14acb906ba6c12f · 100% confidence · shares 3 tags (google, foundational, introduced_in)
Mixture of Experts (MoE) revival popularized in: Shazeer et al. 2017 — outrageously large neural networks via sparse gating.
f068236101568ad7 · 100% confidence · shares 3 tags (google, foundational, introduced_in)
Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research.
6cdc7730bf41bb3d · 100% confidence · shares 3 tags (google, foundational, introduced_in)
Retrieval-Augmented Generation (RAG) introduced in paper: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., 2020).
d15057ced937a103 · 100% confidence · shares 2 tags (rag, foundational)
Frequently asked questions
Is the claim "CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation." verified?
Yes — SourceScore verified this claim with 100% confidence as of 2026-05-16. The verification uses 2 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation."?
Evidence comes from 2 primary sources: arXiv (Yan, Gan, Mao, Zhu, Wu, Xu, Liu, Liu / USTC + Google), USTC team. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/326d6dd16bd353d1.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-16 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/326d6dd16bd353d1.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
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/326d6dd16bd353d1.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/326d6dd16bd353d1.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/326d6dd16bd353d1.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_crag_corrective_rag_fact() -> dict:
"""Fetch the verified SourceScore claim for CRAG (Corrective RAG)."""
r = httpx.get("https://sourcescore.org/api/v1/claims/326d6dd16bd353d1.json")
return r.json()