Paper Citation Record · LEDGER

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

As of 6 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2606.04446.

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

pith.paper-citation-record.v1
2606.04446 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T04:51:28.419612Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

34 of 34 outbound references displayed

verified exact12
verified fuzzy0
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c1a2b347-8e57-43c6-981f-aa113af26c14 · outbound

This paper cites DeepSeek-V3 Technical Report.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models DeepSeek-V3 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.700460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 668be06e-7882-46a6-95bd-37c74bd6f50b · outbound

This paper cites Qwen3 Technical Report.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Qwen3 Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.703182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d602b1f0-7d9a-43f3-b4ef-9aa9a16e46e9 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models GLM-5: from Vibe Coding to Agentic Engineering

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.692876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c8082b2f-913c-4fa1-a10f-eb0d6717d5ad · outbound

This paper cites Fast inference from transformers via speculative decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Fast inference from transformers via speculative decoding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe8194a-1bd9-45b2-90f5-a52ef2a6afde · outbound

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

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Accelerating Large Language Model Decoding with Speculative Sampling

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.694926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b3904077-3084-49b0-a1ff-3979042a0d95 · outbound

This paper cites Specinfer: Accelerating large language model serving with tree-based speculative inference and verification.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Specinfer: Accelerating large language model serving with tree-based speculative inference and verification

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b5056c8-38e7-4d2a-b2e1-11655373fc27 · outbound

This paper cites Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T10:56:52.695567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0062e03a-12de-4c5f-92f0-253f6f85ca7a · outbound

This paper cites Eagle-3: Scaling up inference acceleration of large language models via training-time test.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Eagle-3: Scaling up inference acceleration of large language models via training-time test

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50768005-f73a-4a1a-9611-959a3dca293a · outbound

This paper cites DFlash: Block Diffusion for Flash Speculative Decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models DFlash: Block Diffusion for Flash Speculative Decoding

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T10:56:52.697944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bebd7537-2a76-44e4-bd6a-dc2203eda96a · outbound

This paper cites Fasttree: Optimizing attention kernel and runtime for tree-structured llm inference.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Fasttree: Optimizing attention kernel and runtime for tree-structured llm inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d93fe2e-7a78-4ec9-874a-e765fac2ca1f · outbound

This paper cites Deft: Decoding with flash tree-attention for efficient tree-structured llm inference.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Deft: Decoding with flash tree-attention for efficient tree-structured llm inference

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f390458-d2e3-4bb8-bb02-2573723fee99 · outbound

This paper cites Magicdec: Breaking the latency-throughput tradeoff for long context generation with speculative decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Magicdec: Breaking the latency-throughput tradeoff for long context generation with speculative decoding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c48d962-f621-49cd-8fa1-d6aab29f963a · outbound

This paper cites Glide with a cape: A low-hassle method to accelerate speculative decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Glide with a cape: A low-hassle method to accelerate speculative decoding

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d2bd10-3de2-418b-a7d7-6ca98f4f38c7 · outbound

This paper cites Eagle-2: Faster inference of language models with dynamic draft trees.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Eagle-2: Faster inference of language models with dynamic draft trees

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 176f0543-8c52-43e6-b65d-2940e0aeac04 · outbound

This paper cites Medusa: Simple llm inference acceleration framework with multiple decoding heads.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Medusa: Simple llm inference acceleration framework with multiple decoding heads

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f0c4cef-4606-42d4-af42-198eecc58dbf · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Training Verifiers to Solve Math Word Problems

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.680810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c4976bd1-c18c-48ef-a98f-249d11d03054 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Measuring mathematical problem solving with the math dataset

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 494e50ca-a2ee-4b04-a666-b7d4b0128526 · outbound

This paper cites American Invitational Mathematics Examination – AIME 2025.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models American Invitational Mathematics Examination – AIME 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68d6f51f-4b7c-4e97-abad-0495973711a5 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Evaluating Large Language Models Trained on Code

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.685258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 728c4f68-80e4-46ba-ae3e-07efed1428b8 · outbound

This paper cites Program Synthesis with Large Language Models.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Program Synthesis with Large Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.679926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0a7fd022-77a8-4966-905a-4481592079bc · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6482d9b5-5468-4a67-b817-1275e757bea0 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55389453-755f-4ca2-8950-f2fa818f9d29 · outbound

This paper cites Hashimoto.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Hashimoto

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f946c407-089e-4f4d-9fe5-4ba490d65da6 · outbound

This paper cites The perfect blend: Redefining rlhf with mixture of judges, 2024.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models The perfect blend: Redefining rlhf with mixture of judges, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a7e651-9a1e-49e9-97a7-4d5fdfe66da7 · outbound

This paper cites Flashattention-2: Faster attention with better parallelism and work partitioning.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Flashattention-2: Faster attention with better parallelism and work partitioning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f300ca-e383-448a-a437-789a48fde32f · outbound

This paper cites Flashinfer: Efficient and customizable attention engine for llm inference serving.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Flashinfer: Efficient and customizable attention engine for llm inference serving

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7426a78-4006-4fdc-9041-e43a7dc84afe · outbound

This paper cites Eagle: speculative sampling requires rethinking feature uncertainty.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Eagle: speculative sampling requires rethinking feature uncertainty

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7714e36-1b25-475a-b53b-09a443357960 · outbound

This paper cites Break the sequential dependency of llm inference using lookahead decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Break the sequential dependency of llm inference using lookahead decoding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4271e623-492a-4ec4-949d-f308e4d304fb · outbound

This paper cites Online Speculative Decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Online Speculative Decoding

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T10:56:52.668974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0f68fead-2712-4484-83f2-aae27cb1cf23 · outbound

This paper cites LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.687697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fbdfa311-cd4d-4daf-83d2-98fadafc5b3c · outbound

This paper cites LLaDA2.1 : Speeding up text diffusion via token editing.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models LLaDA2.1 : Speeding up text diffusion via token editing

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-02T10:56:52.682617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 043d9fe5-5e77-4e92-9974-a5af8567d049 · outbound

This paper cites Diffuspec: Unlocking diffusion language models for speculative decoding.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Diffuspec: Unlocking diffusion language models for speculative decoding

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-02T10:56:52.671827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 17f94c82-6834-44be-9b80-e8fec74d0c88 · outbound

This paper cites Pard: Accelerating llm inference with low-cost parallel draft model adaptation, 2025.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Pard: Accelerating llm inference with low-cost parallel draft model adaptation, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T04:51:28.419612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d625fcb-16ac-4dc8-87b6-173994959032 · outbound

This paper cites Accelerating Speculative Decoding with Block Diffusion Draft Trees.

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models Accelerating Speculative Decoding with Block Diffusion Draft Trees

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:56:52.675572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.