Verified claim · AI-ML · 100% confidence
ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 2335984b07f28cac
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Structured fields
- Subject
- ColBERT
- Predicate
introduced_in- Object
- Khattab & Zaharia 2020 — late-interaction retrieval
- Confidence
- 100%
- Tags
- colbert · stanford · retrieval · late-interaction · foundational · sigir · 2020 · introduced_in
Sources (2)
[1] preprint · arXiv / SIGIR 2020 (Khattab, Zaharia / Stanford) · 2020-04-27
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT“We present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval. ColBERT introduces a late interaction architecture that independently encodes the query and the document using BERT and then employs a cheap yet powerful interaction step that models their fine-grained similarity.”
[2] github release · Stanford FutureData · 2020-04-27
ColBERT — official Stanford FutureData repository
Cite this claim
Ready-to-paste citation (Markdown / plain text):
ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval. — SourceScore Claim 2335984b07f28cac (verified 2026-05-16). https://sourcescore.org/api/v1/claims/2335984b07f28cac.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/2335984b07f28cac/" width="100%" height="360" frameborder="0" loading="lazy" title="ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
Retrieval-Augmented Generation (RAG) introduced in paper: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., 2020).
d15057ced937a103 · 100% confidence · shares 3 tags (retrieval, foundational, 2020)
AlphaFold 1 introduced in: Senior et al. 2020 — DeepMind protein structure prediction.
a77a8dd48941a53d · 100% confidence · shares 3 tags (foundational, 2020, introduced_in)
Kaplan scaling laws introduced in paper: Kaplan et al. 2020 — Scaling Laws for Neural Language Models.
22e12bfbe7770657 · 100% confidence · shares 3 tags (foundational, 2020, introduced_in)
Direct Preference Optimization (DPO) introduced in paper: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (Rafailov et al., 2023).
a3e691683a4577af · 100% confidence · shares 2 tags (foundational, stanford)
Vision Transformer (ViT) introduced in paper: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Dosovitskiy et al., 2020).
d3681b0981e0b700 · 100% confidence · shares 2 tags (foundational, 2020)
Frequently asked questions
Is the claim "ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval." 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 "ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval."?
Evidence comes from 2 primary sources: arXiv / SIGIR 2020 (Khattab, Zaharia / Stanford), Stanford FutureData. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/2335984b07f28cac.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/2335984b07f28cac.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/2335984b07f28cac.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/2335984b07f28cac.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/2335984b07f28cac.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "ColBERT introduced in: Khattab & Zaharia 2020 — late-interaction retrieval."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_colbert_fact() -> dict:
"""Fetch the verified SourceScore claim for ColBERT."""
r = httpx.get("https://sourcescore.org/api/v1/claims/2335984b07f28cac.json")
return r.json()