Paper Citation Record · LEDGER

Out-of-Vocabulary Sampling Boosts Speculative Decoding

As of 18 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 1 inbound Pith citation observation for arXiv:2506.03206.

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

pith.paper-citation-record.v1
2506.03206 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:33:42.501449Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T04:20:10.699246Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy4
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation ed2a533b-fa8a-469b-ab36-cd7567fd7742 · outbound

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

Out-of-Vocabulary Sampling Boosts Speculative Decoding Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:40.742405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc15526e-3a10-4d4d-b657-9e2efd1f8871 · outbound

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

Out-of-Vocabulary Sampling Boosts Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:40.812303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31d83682-d816-4f24-aa8a-940613f91ecf · outbound

This paper cites The Llama 3 Herd of Models.

Out-of-Vocabulary Sampling Boosts Speculative Decoding The Llama 3 Herd of Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:40.960865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e30f1ce-9f5a-4df5-9b76-9600065f7b6b · outbound

This paper cites Fast inference from transformers via speculative decoding.

Out-of-Vocabulary Sampling Boosts Speculative Decoding Fast inference from transformers via speculative decoding

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:33:43.586514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c78d1187-d699-435b-9f6b-86b4cdf2b2bd · outbound

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

Out-of-Vocabulary Sampling Boosts Speculative Decoding EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:41.268608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bff5f3fa-58d8-4a86-9ae4-383183fc0712 · outbound

This paper cites EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees.

Out-of-Vocabulary Sampling Boosts Speculative Decoding EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:41.423882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9481148f-b2ab-4385-8907-327c324ef2dd · outbound

This paper cites EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test.

Out-of-Vocabulary Sampling Boosts Speculative Decoding EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:41.567789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a32a669-87ae-4e6f-addb-eb74973607f9 · outbound

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

Out-of-Vocabulary Sampling Boosts Speculative Decoding Specinfer: Accelerating large language model serving with tree-based speculative inference and verification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:41.709001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef774cbc-7be2-4482-bf3d-bebf1deac652 · outbound

This paper cites SlimPajama: A 627B token cleaned and deduplicated version of RedPajama.

Out-of-Vocabulary Sampling Boosts Speculative Decoding SlimPajama: A 627B token cleaned and deduplicated version of RedPajama

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:33:43.347986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5347d77c-0cef-4b77-b7ac-3f9d26b269a8 · outbound

This paper cites Block verification accelerates speculative decoding.

Out-of-Vocabulary Sampling Boosts Speculative Decoding Block verification accelerates speculative decoding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:33:43.146741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 646f90f4-8a71-4fac-948b-0f536134efff · outbound

This paper cites Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies.

Out-of-Vocabulary Sampling Boosts Speculative Decoding Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:42.077850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afd21d28-87c4-4459-864e-d5e768295a44 · outbound

This paper cites Distributed speculative inference ( DSI ): Speculation parallelism for provably faster lossless language model inference.

Out-of-Vocabulary Sampling Boosts Speculative Decoding Distributed speculative inference ( DSI ): Speculation parallelism for provably faster lossless language model inference

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:33:42.915071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5f26514a-ff95-4d22-9e9e-a536a37fe60f · outbound

This paper cites Qwen2.5 Technical Report.

Out-of-Vocabulary Sampling Boosts Speculative Decoding Qwen2.5 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:42.368770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2222308-70e7-4e58-9eed-9346579f41fd · outbound

This paper cites FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling.

Out-of-Vocabulary Sampling Boosts Speculative Decoding FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:33:42.501449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b16d51d8-7c0a-4c41-ada8-f1a1730a9ec6 · inbound

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding cites this paper.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Out-of-Vocabulary Sampling Boosts Speculative Decoding

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.669836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.