Paper Citation Record · LEDGER

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

As of 6 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2507.01449.

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

pith.paper-citation-record.v1
2507.01449 v3

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-19T06:53:02.744567Z

measured 46 of 46 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T08:51:11.662084Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-29T08:53:15.761041Z

Reference resolution

44 of 44 outbound references displayed

verified exact29
verified fuzzy11
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 449d75ec-30c7-4059-95a7-00d133cc5905 · outbound

This paper cites GPT-4 Technical Report.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.176418Z

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 fa2a5a18-5c75-4b50-9ca1-90a047b918e0 · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.172488Z

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 d05f9975-d744-49cd-8c8b-d69e64ecc149 · outbound

This paper cites Qwen2.5 Technical Report.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Qwen2.5 Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.162995Z

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 cf1831cc-fe68-4330-9047-f1ff1af987ca · outbound

This paper cites The Llama 3 Herd of Models.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation The Llama 3 Herd of Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.184916Z

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 f89200ca-6b83-45a1-beae-1f90a3c07e85 · outbound

This paper cites A literature review on question answering techniques, paradigms and systems.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation A literature review on question answering techniques, paradigms and systems

Reference 5

Resolution: verified exact; doi, observed 2026-05-19T06:57:07.694847Z

Source-reported events for the cited work

correction dated 2020-11-24. Source: crossref record 10.1016/j.jksuci.2020.11.015->10.1016/j.jksuci.2018.08.005:correction, observed 2026-07-11T03:10:57.907759+00:00. This notice travels one citation hop only.

Observation de3152e7-7f50-4f51-9250-a359b6c4a8e7 · outbound

This paper cites A Survey on Large Language Models for Code Generation.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation A Survey on Large Language Models for Code Generation

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.189550Z

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 2debbe80-b187-4925-9589-fe5de24149d8 · outbound

This paper cites A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.167742Z

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 179692f7-7061-475f-862a-14503cb7e58d · outbound

This paper cites Fast inference from transformers via speculative decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Fast inference from transformers via speculative decoding

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.963668Z

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 5aed4338-ed2e-467f-a785-ffc13a879e76 · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Accelerating Large Language Model Decoding with Speculative Sampling

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.180556Z

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 97452a54-83d3-485c-b1f7-fc4bab9ccb60 · outbound

This paper cites PEARL : Parallel speculative decoding with adaptive draft length.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation PEARL : Parallel speculative decoding with adaptive draft length

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.966870Z

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 4a834c8d-220a-471b-90b4-8620bd087dcd · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.157988Z

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 c10c9f6d-b2aa-4641-964f-72f0022b1c0b · outbound

This paper cites Prompt lookup decoding, November 2023.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Prompt lookup decoding, November 2023

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.960270Z

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 e5dac906-1699-4a09-81b9-5581154de82f · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Break the sequential dependency of llm inference using lookahead decoding

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.969889Z

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 1476bf48-dcee-42a7-bc81-e9353df1a2a4 · outbound

This paper cites REST : Retrieval-based speculative decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation REST : Retrieval-based speculative decoding

Reference 14

Resolution: verified exact; doi, observed 2026-05-19T06:57:07.684371Z

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 8a0d9f78-7b9a-42c2-906e-11faae93ec84 · outbound

This paper cites Lee, Deming Chen, and Tri Dao.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Lee, Deming Chen, and Tri Dao

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.990096Z

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 b685de85-7fae-484b-836c-dfaab4041ea6 · outbound

This paper cites Hydra: Sequentially-dependent draft heads for medusa decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Hydra: Sequentially-dependent draft heads for medusa decoding

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.987102Z

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 14dafdaf-dcd8-4514-b109-ba5175e81103 · outbound

This paper cites Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.072937Z

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 75a57627-e671-4ecc-a770-edab50cf7327 · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Glide with a cape: a low-hassle method to accelerate speculative decoding

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.993349Z

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 8454cdb8-3719-4a26-a347-a22faa81bf3d · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.078215Z

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 7bfc0cca-f048-4dfd-9c07-14a83abde9b6 · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation EAGLE -2: Faster inference of language models with dynamic draft trees

Reference 20

Resolution: verified exact; doi, observed 2026-05-19T06:57:07.688103Z

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 fe8616eb-819f-4de3-b854-2f586f9929bc · outbound

This paper cites An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al

Reference 21

Resolution: metadata mismatch; doi, observed 2026-05-19T06:57:07.680775Z

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 999f06f0-d54d-4884-a8d4-e8224cc9e040 · outbound

This paper cites Layerskip: Enabling early exit inference and self-speculative decoding, August 2024.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Layerskip: Enabling early exit inference and self-speculative decoding, August 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.997539Z

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 8332a367-4a86-4ef0-b4ca-6166c54bca9f · outbound

This paper cites SWIFT : On-the-fly self-speculative decoding for LLM inference acceleration.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation SWIFT : On-the-fly self-speculative decoding for LLM inference acceleration

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.983203Z

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 6764b41d-4ee8-4f51-9233-32f010cda71a · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Better & Faster Large Language Models via Multi-token Prediction

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.114826Z

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 c7ab0fbb-0a2e-4cf9-b8bb-5a8ebb9d665b · outbound

This paper cites Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding

Reference 25

Resolution: verified exact; doi, observed 2026-05-19T06:57:07.691485Z

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 f9ff4ddd-f9c4-4903-9207-6c3ae186342a · outbound

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

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Specinfer: Accelerating large language model serving with tree-based speculative inference and verification

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:07.670470Z

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 3f923c47-44d8-4b3c-afa3-9db5c59c5a17 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Evaluating Large Language Models Trained on Code

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.119876Z

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 b0823f8b-03df-45bf-9abb-bd6b32a51123 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Training Verifiers to Solve Math Word Problems

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.109871Z

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 42fddce5-9517-409c-b75c-5f552002168b · outbound

This paper cites doi: 10.18653/v1/K16-1028.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation doi: 10.18653/v1/K16-1028

Reference 29

Resolution: metadata mismatch; doi, observed 2026-05-19T06:57:07.675556Z

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 f46ed9df-2044-4ca4-9554-4804ec0797e7 · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:57:08.129890Z

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 c7081234-a92b-49a4-b847-6f447c1a7851 · outbound

This paper cites an unresolved cited work.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:57:09.001195Z

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 58015956-5278-4b43-81ea-880f59240af7 · outbound

This paper cites an unresolved cited work.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Unresolved cited work

Reference 32

Resolution: malformed identifier; raw_fallback, observed 2026-05-19T06:57:08.976313Z

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 6bd0b6f5-9e1a-4f4e-8060-912879c9bfcf · outbound

This paper cites Learning harmonized representations for speculative sampling.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Learning harmonized representations for speculative sampling

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.979582Z

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 705a7607-254e-48fa-aa1d-17d3eba5bdb0 · outbound

This paper cites CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.125103Z

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 2c564df3-6203-45b1-8ebc-7fbf0db78e40 · outbound

This paper cites Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.105128Z

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 b3508aa2-8d2e-4923-b84c-1ad52d8633d4 · outbound

This paper cites Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.095013Z

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 c16603b6-fb3a-4fbc-8329-d993895b2d7b · outbound

This paper cites Specdec++: Boosting speculative decoding via adaptive candidate lengths.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Specdec++: Boosting speculative decoding via adaptive candidate lengths

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:57:08.972900Z

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 9ee1140b-8668-434f-a425-165eb6ee4be3 · outbound

This paper cites OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.147003Z

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 c74aa8a4-11e6-45e3-8260-f48ea7ff17a7 · outbound

This paper cites AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.140921Z

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 9c1bed11-a931-4505-9992-8c898b93414c · outbound

This paper cites SPEED: Speculative Pipelined Execution for Efficient Decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation SPEED: Speculative Pipelined Execution for Efficient Decoding

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.135410Z

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 85e0fd8a-988d-49e2-8754-1092f8090124 · outbound

This paper cites Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.152830Z

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 49b79bff-a0fd-4418-b1d9-9897c96311cc · outbound

This paper cites Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.083769Z

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 f223c0e0-0473-4930-a912-bdac43ab6c89 · outbound

This paper cites Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.089239Z

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 fe5b3c85-e7d6-4101-a79c-acd4cb38bd1e · outbound

This paper cites SAM Decoding: Speculative Decoding via Suffix Automaton.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation SAM Decoding: Speculative Decoding via Suffix Automaton

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:57:08.099694Z

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

Observation 52f544e3-f051-4bcf-b5b7-d7b3c267c899 · inbound

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding cites this paper.

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:03:06.485380Z

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 0402ea6c-6eb6-41e0-8fbd-c6393388b90b · inbound

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting cites this paper.

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-06-29T08:53:15.762859Z

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.