Paper Citation Record · LEDGER

Scaling Speculative Decoding with Lookahead Reasoning

As of 18 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 2 inbound Pith citation observations for arXiv:2506.19830.

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

pith.paper-citation-record.v1
2506.19830 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:32:08.097781Z

measured 45 of 45 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:33:45.824727Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T19:20:06.659443Z

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy12
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f5d38717-b509-4740-9f32-9c116e9dab2a · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Scaling Speculative Decoding with Lookahead Reasoning Chain-of-thought prompting elicits reasoning in large language models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.925098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4cb6e4-fb10-4418-a62e-020b0a638b28 · outbound

This paper cites an unresolved cited work.

Scaling Speculative Decoding with Lookahead Reasoning Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.929784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ddff7f8-bde4-4484-9330-2e165c72034f · outbound

This paper cites Fast inference from transformers via speculative decoding.

Scaling Speculative Decoding with Lookahead Reasoning Fast inference from transformers via speculative decoding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.935280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f1d8968-ef6a-40c1-babb-b6432483c1de · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.938894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 566f83b6-bb38-4fd3-bd49-4e9bdef00595 · outbound

This paper cites Openai o3 and o4-mini system card.

Scaling Speculative Decoding with Lookahead Reasoning Openai o3 and o4-mini system card

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.614487Z

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 c713e366-bd20-46e2-9c1a-2ba9baef6635 · outbound

This paper cites Qwen3 technical report.

Scaling Speculative Decoding with Lookahead Reasoning Qwen3 technical report

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.601135Z

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 c0b60a8b-6ccd-4c13-8cbe-21ecfa7d2407 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023.

Scaling Speculative Decoding with Lookahead Reasoning Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.950060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aea39a30-0678-4cce-bdd3-b9f61a87b0af · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert- networks.

Scaling Speculative Decoding with Lookahead Reasoning Sentence-bert: Sentence embeddings using siamese bert- networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.954130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5f7a379-7b18-41d7-979a-65878cfcde1f · outbound

This paper cites SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning.

Scaling Speculative Decoding with Lookahead Reasoning SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.957611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d5f4786-de90-43ef-99cd-6a87b22abfb6 · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.961938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f8cb341-c3d9-448c-8759-49fc01680224 · outbound

This paper cites Qwen2.5 Technical Report.

Scaling Speculative Decoding with Lookahead Reasoning Qwen2.5 Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.967277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3024e64-8314-4b8a-999c-d93988f42377 · outbound

This paper cites Break the Sequential Dependency of LLM Inference Using Lookahead Decoding.

Scaling Speculative Decoding with Lookahead Reasoning Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.971833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dab908b0-3347-4c9d-93b9-4e3e5b447a5f · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.976135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb1b114-8c13-4147-b994-98359141e66e · outbound

This paper cites an unresolved cited work.

Scaling Speculative Decoding with Lookahead Reasoning Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.980402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022f0560-e4f3-457c-ac3f-d06a86f9e28b · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Scaling Speculative Decoding with Lookahead Reasoning LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.984338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1ab1454-5e50-47d6-b095-2d4312ced9f3 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Scaling Speculative Decoding with Lookahead Reasoning Training Verifiers to Solve Math Word Problems

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:07.988503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51b39564-5c6b-4b1f-9e78-6998cc7b6993 · outbound

This paper cites Aime problems and solutions, 2025.

Scaling Speculative Decoding with Lookahead Reasoning Aime problems and solutions, 2025

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.564027Z

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 95679846-196b-444a-8b6a-0174a579525e · outbound

This paper cites Amc 12 problems and solutions, 2025.

Scaling Speculative Decoding with Lookahead Reasoning Amc 12 problems and solutions, 2025

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.551404Z

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 fc502e3a-1141-4609-a450-3942f05a216b · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Scaling Speculative Decoding with Lookahead Reasoning Gpqa: A graduate-level google-proof q&a benchmark

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.000667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bd0c4bd-1b4b-40d6-b57c-a65df232e4a6 · outbound

This paper cites Qwen2.5-math: The world’s leading open-sourced mathematical llms, 2024.

Scaling Speculative Decoding with Lookahead Reasoning Qwen2.5-math: The world’s leading open-sourced mathematical llms, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.531143Z

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 2f5e024e-e42e-4e8e-b373-6feccbdac6a6 · outbound

This paper cites Prompt lookup decoding, November 2023.

Scaling Speculative Decoding with Lookahead Reasoning Prompt lookup decoding, November 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.009179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 342a5fe4-da50-4ad3-874c-3279a33ead80 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Scaling Speculative Decoding with Lookahead Reasoning Efficient memory management for large language model serving with pagedattention

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.508832Z

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 55373592-97b5-4273-9bc7-9ec7394a3560 · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.017180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c106fec-83e5-4331-8ed6-322d8ae1f5b4 · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.020747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ba10939-5524-4d2b-85d0-9dad8fdec7ac · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.024399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74bfa710-1877-4d90-b2dc-c614220fef1e · outbound

This paper cites Cllms: Consistency large language models.

Scaling Speculative Decoding with Lookahead Reasoning Cllms: Consistency large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.496183Z

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 30243f37-9666-475c-adfe-612553dde89b · outbound

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

Scaling Speculative Decoding with Lookahead Reasoning SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.031433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1fe6167-90e8-4588-b0b9-1a656c3720d1 · outbound

This paper cites TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput.

Scaling Speculative Decoding with Lookahead Reasoning TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.035559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dad4dbc-0134-401b-9181-1c9f1c5e83d9 · outbound

This paper cites DeepSeek-V3 Technical Report.

Scaling Speculative Decoding with Lookahead Reasoning DeepSeek-V3 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.039844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a69af320-8d46-407e-b2e3-046d5656aabe · outbound

This paper cites GPT-4 Technical Report.

Scaling Speculative Decoding with Lookahead Reasoning GPT-4 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.043989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b91f016-0995-45e5-8dbc-357301bcac21 · outbound

This paper cites s1: Simple test-time scaling.

Scaling Speculative Decoding with Lookahead Reasoning s1: Simple test-time scaling

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.047857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 546a28c3-d968-4578-933d-2d8796b9ed9f · outbound

This paper cites From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models.

Scaling Speculative Decoding with Lookahead Reasoning From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.052030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1574ac63-f783-483a-a47e-ec878986a50e · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Scaling Speculative Decoding with Lookahead Reasoning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.056063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5a74ab-d67a-46c1-b85a-d3c37daf2e11 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Scaling Speculative Decoding with Lookahead Reasoning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.060326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97f082df-3bb4-4d0b-8620-fd461d233def · outbound

This paper cites Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time.

Scaling Speculative Decoding with Lookahead Reasoning Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T18:32:08.064506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01cef315-3647-45bb-8588-195c5c376384 · outbound

This paper cites The draft model sequentially generate drafts.

Scaling Speculative Decoding with Lookahead Reasoning The draft model sequentially generate drafts

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.483511Z

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 1b3eeee9-c196-4637-b32b-403ede5e3bce · outbound

This paper cites an unresolved cited work.

Scaling Speculative Decoding with Lookahead Reasoning Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:32:08.469993Z

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 5922a616-2347-4814-8b36-198bdb08c561 · outbound

This paper cites If the draft was reject, fall back to the target model’s original sentence and proceed to the nextDRAFT STAGE.

Scaling Speculative Decoding with Lookahead Reasoning If the draft was reject, fall back to the target model’s original sentence and proceed to the nextDRAFT STAGE

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.456819Z

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 c87a5fc4-29f7-4cfe-9ff1-bcd7f7b21daf · outbound

This paper cites The parallel dimension of the target model is ⌈ 1 c1 ⌉, and asn→∞, the asymptotic speedup is S1 = 1 c1 + (1−c 1)(1−α 1).

Scaling Speculative Decoding with Lookahead Reasoning The parallel dimension of the target model is ⌈ 1 c1 ⌉, and asn→∞, the asymptotic speedup is S1 = 1 c1 + (1−c 1)(1−α 1)

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.442311Z

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 e4c24414-b548-4a8f-9759-68aba93181df · outbound

This paper cites The parallel dimension of the target model isγ, and asn→∞, the asymptotic speedup is S2 = 1−α γ 1 (1−α 1) +c 1 α1−αγ+1 1 −γ(1−α 1)αγ 1.

Scaling Speculative Decoding with Lookahead Reasoning The parallel dimension of the target model isγ, and asn→∞, the asymptotic speedup is S2 = 1−α γ 1 (1−α 1) +c 1 α1−αγ+1 1 −γ(1−α 1)αγ 1

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.429842Z

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 e4adfac2-5dbd-4453-8232-06f19a7ce690 · outbound

This paper cites an unresolved cited work.

Scaling Speculative Decoding with Lookahead Reasoning Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:32:08.417077Z

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 accd12ff-9fab-4038-93a1-81a295fbc3e6 · outbound

This paper cites an unresolved cited work.

Scaling Speculative Decoding with Lookahead Reasoning Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:32:08.404058Z

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 2ea6f168-cd0e-4fb9-bb29-380f66329fca · outbound

This paper cites Proof.(i) Monotonicity inx.Fixα∈(0,1)and write f(x) = xαx 1−α x = N(x) D(x), N(x) =xα x, D(x) = 1−α x.

Scaling Speculative Decoding with Lookahead Reasoning Proof.(i) Monotonicity inx.Fixα∈(0,1)and write f(x) = xαx 1−α x = N(x) D(x), N(x) =xα x, D(x) = 1−α x

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:32:08.391178Z

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.

Pith citing papers

Observation db1ffe45-2c1b-4f04-8758-b1926160c02d · inbound

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing cites this paper.

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing Scaling Speculative Decoding with Lookahead Reasoning

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-04T19:20:06.661156Z

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 d37e6543-5a21-4604-96e4-da000e941197 · inbound

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing cites this paper.

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing Scaling Speculative Decoding with Lookahead Reasoning

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:35:29.625090Z

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.