Paper Citation Record · LEDGER

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

As of 10 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 3 inbound Pith citation observations for arXiv:2502.06282.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.06282 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T16:12:29.003107Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T21:08:29.233848Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-12T08:40:41.670402Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy3
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f884bab6-ac51-4e5e-b762-2bf828d90301 · outbound

This paper cites Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.600149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e729bbe-b16a-4451-b2e9-224ae6d3c0c7 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Accelerating Large Language Model Decoding with Speculative Sampling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.719796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e338f42-b959-4484-9153-5ae547bfbe16 · outbound

This paper cites DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.731398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bce880c-a622-479c-9517-99ccbb98a1ad · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.736999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e132727a-6662-497e-bfb9-f076ae469a48 · outbound

This paper cites URL https://doi.org/ 10.18653/v1/2022.acl-long.489.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE URL https://doi.org/ 10.18653/v1/2022.acl-long.489

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.747736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a44266-bcfe-4f2c-9020-62900aded5a1 · outbound

This paper cites The Llama 3 Herd of Models.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.767844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b21138b6-a5d9-4917-8968-b42ce5c6347e · outbound

This paper cites Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.803450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b6f7776-1fa1-4f32-a2f2-823cce307eb1 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.851712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af491f6d-2acc-400c-969b-9c9ff6549d97 · outbound

This paper cites Mixtral of Experts.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Mixtral of Experts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.862322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 474ecf65-4c8e-4552-9d5c-53b895f8eedf · outbound

This paper cites Crafting papers on machine learning.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Crafting papers on machine learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.872124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da351026-4d11-4b83-a666-09db98255bc9 · outbound

This paper cites Contrastive Decoding: Open-ended Text Generation as Optimization.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Contrastive Decoding: Open-ended Text Generation as Optimization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.877138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da4b6d6f-363f-48f0-8e87-2471d32ebda5 · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.882739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b17e9eeb-c3b0-4415-9ecd-2f57792989f9 · outbound

This paper cites SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.888564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d9080f2-e0a0-4cff-903e-92c91b7322af · outbound

This paper cites PaSS: Parallel Speculative Sampling.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE PaSS: Parallel Speculative Sampling

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.893367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4edc6f5-7857-4b8a-8bb7-3bd0c4337de6 · outbound

This paper cites Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.914574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fcb2dfe-9410-4471-b1d6-9ea6841abe07 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Fast Transformer Decoding: One Write-Head is All You Need

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.967060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f01c38-99fe-4aff-bc26-7a9c44931861 · outbound

This paper cites A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.983368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd7cfd9-a3be-4322-b895-9ca44f433103 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE LLaMA: Open and Efficient Foundation Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.988275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f738c5d-bf30-4c14-9d3d-1108f790f33a · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.993285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 570e4780-b17d-4ada-a99c-8c36d0044fc8 · outbound

This paper cites Generation meets verification: Accelerating large lan- guage model inference with smart parallel auto-correct decoding.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Generation meets verification: Accelerating large lan- guage model inference with smart parallel auto-correct decoding

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:12:29.494735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9955b05b-532c-4eca-98a7-0352464f36d9 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:29.003107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecc449cf-0676-4e5f-8f50-3ca8d813c063 · outbound

This paper cites OpenAI o1 System Card.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE OpenAI o1 System Card

Reference 1991

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.856639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ccf0ad-a702-4ade-b574-6480e58bd482 · outbound

This paper cites 1162/neco.1994.6.2.181.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE 1162/neco.1994.6.2.181

Reference 1994

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:12:29.519818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c6174ef1-abbd-4bb5-946a-8c8cad82e328 · outbound

This paper cites Contrastive Decoding Improves Reasoning in Large Language Models.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Contrastive Decoding Improves Reasoning in Large Language Models

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.944851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21879fa-9f4a-431d-874f-8d328aec1310 · outbound

This paper cites Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast

Reference 2017

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T16:12:29.136455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1fe85545-1999-42b1-9176-8a732949e3b6 · outbound

This paper cites Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.978206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57464e7c-6901-4ed4-8eea-db7ab24109e1 · outbound

This paper cites Better & Faster Large Language Models via Multi-token Prediction.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Better & Faster Large Language Models via Multi-token Prediction

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.826267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ef77de-1e96-46c5-b767-7d30a30e71a6 · outbound

This paper cites Stablemoe: Stable routing strategy for mixture of experts.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Stablemoe: Stable routing strategy for mixture of experts

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:12:29.535269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c9cea444-63b4-48fe-82cf-0ee6ddb737e8 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.678565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 886a97bc-2c02-4d90-8038-ce236e2d5a4a · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Evaluating Large Language Models Trained on Code

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.725560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe40e5e0-e9ef-4347-887d-1329cbbe5dab · outbound

This paper cites Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.631982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 29553447-b171-4959-9441-10f2afb7c03a · inbound

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models cites this paper.

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

Reference 285

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:40:41.672843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 68fa8e58-4876-40ce-9b54-5dfa87a0838b · inbound

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference cites this paper.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.528129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65d5aa5c-6c44-4655-8b74-163e69737c36 · inbound

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks cites this paper.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:29.233848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.