Verified claim · AI-ML · 100% confidence
Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 6cdc7730bf41bb3d
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Related verified claims
More verified claims related to this one — keep exploring.
Chain-of-Thought prompting introduced in paper: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Wei et al., 2022).
100% confidence · shares 3 tags (foundational, 2022, google)
Batch Normalization introduced in paper: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (Ioffe & Szegedy, 2015).
100% confidence · shares 3 tags (foundational, icml, google)
PaLM introduced in paper: PaLM: Scaling Language Modeling with Pathways (Chowdhery et al., 2022).
100% confidence · shares 3 tags (google, foundational, 2022)
Imagen introduced in paper: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Saharia et al., 2022).
100% confidence · shares 3 tags (google, foundational, 2022)
GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models.
100% confidence · shares 3 tags (inference, 2022, introduced_in)
Knowledge Distillation popularized in: Hinton, Vinyals, Dean 2015 — distilling the knowledge in a neural network.
100% confidence · shares 3 tags (google, foundational, introduced_in)
InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT.
100% confidence · shares 3 tags (foundational, 2022, introduced_in)
Mixture of Experts (MoE) revival popularized in: Shazeer et al. 2017 — outrageously large neural networks via sparse gating.
100% confidence · shares 3 tags (google, foundational, introduced_in)
Structured fields
- Subject
- Speculative decoding
- Predicate
introduced_in- Object
- Leviathan, Kalman, Matias 2023 — Google Research
- Confidence
- 100%
- Tags
- speculative-decoding · google · inference · foundational · icml · 2022 · introduced_in
Sources (2)
[1] preprint · arXiv (Leviathan, Kalman, Matias / Google Research) · 2022-11-30
Fast Inference from Transformers via Speculative Decoding“Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any changes to the outputs, by computing several tokens in parallel.”
[2] peer reviewed · PMLR / ICML 2023 · 2023-07-23
Speculative Decoding — ICML 2023 proceedings
Cite this claim
Ready-to-paste citation (Markdown / plain text):
Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research. — SourceScore Claim 6cdc7730bf41bb3d (verified 2026-05-16). https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the claim record + top cited source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/6cdc7730bf41bb3d/" width="100%" height="360" frameborder="0" loading="lazy" title="Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research."></iframe>Preview: open in new tab
Frequently asked questions
How has SourceScore reviewed the claim "Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research."?
SourceScore records this assertion with 100% legacy editorial confidence as of 2026-05-16, under methodology veritas-v0.1. That metadata is not a truth guarantee. Inspect the 2 cited source record(s), excerpts, and live evidence below.
What is the evidence for "Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research."?
The record lists 2 cited source(s): arXiv (Leviathan, Kalman, Matias / Google Research), PMLR / ICML 2023. Each is shown below with a short excerpt and URL. The JSON record at https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.json includes SourceScore-issued HMAC integrity metadata, not a public verification proof.
When was this claim record last reviewed by SourceScore?
Last reviewed 2026-05-16 under methodology version veritas-v0.1. The dated JSON record includes SourceScore-issued HMAC metadata, which is not publicly recomputable. Refetch the record and inspect current evidence before relying on it.
How can I cite this SourceScore claim in my code or article?
Fetch the JSON record from https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.json, including the verbatim claim, cited evidence, confidence, methodology version, and last-verified date. Refetch the canonical HTTPS record and inspect cited evidence; the HMAC tag is not publicly independently verifiable. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
Use this claim in your code
Fetch this record from your application. The response includes verbatim excerpts, primary-source URLs, and SourceScore-issued HMAC integrity metadata. Refetch the canonical HTTPS record and inspect cited evidence; public users cannot independently verify the HMAC tag.
cURL
curl https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_speculative_decoding_fact() -> dict:
"""Fetch the verified SourceScore claim for Speculative decoding."""
r = httpx.get("https://sourcescore.org/api/v1/claims/6cdc7730bf41bb3d.json")
return r.json()