Verified claim · AI-ML · 100% confidence
GraphRAG introduced in: Edge et al. 2024 — Microsoft Research knowledge-graph RAG.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 58a9c41f05c73a22
Structured fields
- Subject
- GraphRAG
- Predicate
introduced_in- Object
- Edge et al. 2024 — Microsoft Research knowledge-graph RAG
- Confidence
- 100%
- Tags
- graphrag · microsoft · rag · knowledge-graph · foundational · 2024 · introduced_in
Sources (2)
[1] preprint · arXiv (Edge, Trinh, Cheng, Bradley, Chao, Mody, Truitt, Larson / Microsoft Research) · 2024-04-24
From Local to Global: A Graph RAG Approach to Query-Focused Summarization“We present a Graph RAG approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed.”
[2] github release · Microsoft Research · 2024-07-02
GraphRAG — official Microsoft Research repository
Cite this claim
Ready-to-paste citation (Markdown / plain text):
GraphRAG introduced in: Edge et al. 2024 — Microsoft Research knowledge-graph RAG. — SourceScore Claim 58a9c41f05c73a22 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/58a9c41f05c73a22.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/58a9c41f05c73a22/" width="100%" height="360" frameborder="0" loading="lazy" title="GraphRAG introduced in: Edge et al. 2024 — Microsoft Research knowledge-graph RAG."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
CRAG (Corrective RAG) introduced in: Yan et al. 2024 — corrective retrieval-augmented generation.
326d6dd16bd353d1 · 100% confidence · shares 4 tags (rag, foundational, 2024…)
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)
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, microsoft)
ResNet (Residual Networks) introduced in paper: Deep Residual Learning for Image Recognition (He et al., 2015).
4f55f77c4bfb316e · 100% confidence · shares 2 tags (foundational, microsoft)
Phi-3 (Microsoft small language model family) released on: 2024-04-23.
2d20c4a92620ba46 · 100% confidence · shares 2 tags (microsoft, 2024)
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/58a9c41f05c73a22.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/58a9c41f05c73a22.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "GraphRAG introduced in: Edge et al. 2024 — Microsoft Research knowledge-graph RAG."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/58a9c41f05c73a22.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "GraphRAG introduced in: Edge et al. 2024 — Microsoft Research knowledge-graph RAG."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_graphrag_fact() -> dict:
"""Fetch the verified SourceScore claim for GraphRAG."""
r = httpx.get("https://sourcescore.org/api/v1/claims/58a9c41f05c73a22.json")
return r.json()