Paper Citation Record · LEDGER

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

As of 13 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 1 inbound Pith citation observation for arXiv:2603.25702.

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

pith.paper-citation-record.v1
2603.25702 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T18:04:43.103159Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-02T19:05:59.651008Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T19:07:17.196322Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4829eb2a-6f8a-4f22-aa28-c6993fa45988 · outbound

This paper cites Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5500d6a-2e2c-4da7-a14e-173a816aacc1 · outbound

This paper cites Program Synthesis with Large Language Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Program Synthesis with Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4ea8734-dcde-41b0-9b76-3f33d12db70f · outbound

This paper cites an unresolved cited work.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364f4169-c0e8-42c0-9ec1-7464df6e989c · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df6062e7-bdd6-4361-8ae5-94b9e0c96894 · outbound

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

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Accelerating Large Language Model Decoding with Speculative Sampling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d56dc2c3-b0e3-44de-ba24-0bf397b3141e · outbound

This paper cites Evaluating Large Language Models Trained on Code.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Evaluating Large Language Models Trained on Code

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5e646e0-0031-41cb-9145-a9e7f3057500 · outbound

This paper cites Sdar: A synergistic diffusion- autoregression paradigm for scalable sequence generation.arXiv preprint arXiv:2510.06303,.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Sdar: A synergistic diffusion- autoregression paradigm for scalable sequence generation.arXiv preprint arXiv:2510.06303,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e536e719-58ca-449e-982e-4787a9209db3 · outbound

This paper cites Diffusion Posterior Sampling for General Noisy Inverse Problems.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Diffusion Posterior Sampling for General Noisy Inverse Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaaac26e-cad6-4668-8187-0d302c3366e6 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b798df-7ff5-48ab-bde6-0dba62eae9d7 · outbound

This paper cites 10 Preprint.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation 10 Preprint

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc13c5b0-a12a-4e8d-9ce4-3f45114246d9 · outbound

This paper cites Scaling Diffusion Language Models via Adaptation from Autoregressive Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51c7a66-1170-4051-a65d-19dcee1f0a86 · outbound

This paper cites DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 708100e4-986f-4eac-b85b-692a3a7e03bc · outbound

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

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4277ab7-b59f-445f-bd19-47f69a5d823e · outbound

This paper cites Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd36c94d-0c3c-44b0-aec0-791d2332b0e7 · outbound

This paper cites Autoregressive Diffusion Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Autoregressive Diffusion Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5758b39c-06d0-435f-a73f-c67fa53df06c · outbound

This paper cites OpenAI o1 System Card.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation OpenAI o1 System Card

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3780ceec-99a9-47ae-a38c-1b9d165e823a · outbound

This paper cites Mercury: Ultra-Fast Language Models Based on Diffusion.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Mercury: Ultra-Fast Language Models Based on Diffusion

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ce1caa-b2da-41a2-9a9f-fdf2b0eb0851 · outbound

This paper cites Refusion: A diffusion large language model with parallel autoregressive decoding.arXiv preprint arXiv:2512.13586,.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Refusion: A diffusion large language model with parallel autoregressive decoding.arXiv preprint arXiv:2512.13586,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a44d21-51ad-424a-90e4-5ee8e942077b · outbound

This paper cites Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aa6d7d5-d265-404d-87ce-be380ec7dd4f · outbound

This paper cites Large Language Diffusion Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Large Language Diffusion Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb1cb518-da32-434c-9f71-3c5839a46b04 · outbound

This paper cites Esoteric Language Models: A Family of Any-Order Diffusion LLMs.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Esoteric Language Models: A Family of Any-Order Diffusion LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09ead617-5a96-4fc0-a609-2e4d0c547aed · outbound

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

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47a1290f-5742-4fe3-bd48-d83febc5e97a · outbound

This paper cites Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f090f280-44ea-414e-8f89-19a32685d396 · outbound

This paper cites Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 823489ff-9d51-4cb4-b503-729c188bfe32 · outbound

This paper cites Dream 7B: Diffusion Large Language Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Dream 7B: Diffusion Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5838c8-507e-43b3-a947-d79ac92f4a06 · outbound

This paper cites Redi: Rectified discrete flow.arXiv preprint arXiv:2507.15897,.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Redi: Rectified discrete flow.arXiv preprint arXiv:2507.15897,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b08e058c-6a18-40fd-ac36-ef4215294e58 · outbound

This paper cites T3d: Few-step diffusion language models via trajectory self-distillation with direct discriminative optimization.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation T3d: Few-step diffusion language models via trajectory self-distillation with direct discriminative optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eae701c-c172-4617-9ca3-4db8af900d0f · outbound

This paper cites Variational masked diffusion models.arXiv preprint arXiv:2510.23606,.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Variational masked diffusion models.arXiv preprint arXiv:2510.23606,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593c4f96-9124-42ac-8815-f9b576ada248 · outbound

This paper cites Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d02f3d94-db22-4a46-bb10-cec9f9184889 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Instruction-Following Evaluation for Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59953967-e650-42af-b8a0-8b1cd7263fcc · outbound

This paper cites Instead, after a draft forward pass, it selects which positions to unmask using token confidence, either according to a fixed schedule or a dynamic threshold.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Instead, after a draft forward pass, it selects which positions to unmask using token confidence, either according to a fixed schedule or a dynamic threshold

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 848e11d9-6f69-4ac9-93ab-37d2ee01aa66 · outbound

This paper cites an unresolved cited work.

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T18:04:43.103159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 443aa055-7659-442c-847a-134bbc50d529 · inbound

SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing cites this paper.

SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-02T19:07:17.197492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.