Paper Citation Record · LEDGER

Automatic Task Detection and Heterogeneous LLM Speculative Decoding

As of 16 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2505.08600.

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

pith.paper-citation-record.v1
2505.08600 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:57:56.257387Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

49 of 49 outbound references displayed

verified exact0
verified fuzzy1
unresolved47
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4e796b56-b78c-4f3f-b406-a5e9e17b3deb · outbound

This paper cites Language Models are Few-Shot Learners.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Language Models are Few-Shot Learners

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.832004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e89ceb-6b33-43a8-84c0-75555b8a5afc · outbound

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

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Lee, Deming Chen, and Tri Dao

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.839668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5db17208-c70a-4ef1-b0c0-371dc0e74c51 · outbound

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

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.848353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e5ff1b-7e0e-4289-8927-157494707170 · outbound

This paper cites MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.858173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20b5e177-a57d-4b8f-af6a-3c05e76a7287 · outbound

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

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.865200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6688dd41-bf79-4098-9fd3-f432828115ea · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.874063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b78b656c-fd33-4ea8-b37c-61b10237bb90 · outbound

This paper cites Cascade Speculative Drafting for Even Faster LLM Inference.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Cascade Speculative Drafting for Even Faster LLM Inference

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.892172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f27445aa-71c5-420f-af18-28a0015b5e07 · outbound

This paper cites Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.901839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da05a82c-c238-4864-83c7-0f3ea2aff1b0 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.914069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 748f7334-4c0b-46d4-becd-ebff96844b8c · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.926321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b223720-55d4-4a17-a0a0-7e61a7a07a09 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.486454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ca44c8a3-5a76-4346-b874-60240d3f0eab · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.944811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a53884f-b397-4004-a5f7-484be7fd56e0 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.443921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6243c10b-3d22-4ed9-8b4b-ca58311e489c · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 14

Resolution: malformed identifier; no resolver link, observed 2026-08-15T21:57:55.957680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1e91118-4923-4e6d-bb99-5158524a7ff7 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.964744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 740f6d86-282a-4111-b2bb-820d031e88db · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.415316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7cc7673f-8783-4899-91d8-282a7dbc5f76 · outbound

This paper cites WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.983891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb934cc-57ab-464b-b918-8d7c85b7f7f5 · outbound

This paper cites OpenDataLab: Empowering General Artificial Intelligence with Open Datasets.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding OpenDataLab: Empowering General Artificial Intelligence with Open Datasets

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:55.992085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd631ba5-f075-4a1c-b271-cc999f9f089e · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.000511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af78205-7787-4add-bf1c-a284462b314d · outbound

This paper cites REST: Retrieval-Based Speculative Decoding.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding REST: Retrieval-Based Speculative Decoding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.010851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d72502d-3463-442c-a484-3fa5c091eda6 · outbound

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

Automatic Task Detection and Heterogeneous LLM Speculative Decoding SPEED: Speculative Pipelined Execution for Efficient Decoding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.019975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610fb837-86c4-4af0-8e21-7b34af742d74 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding LoRA: Low-Rank Adaptation of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.027145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a008b86-f0f8-49a9-950a-ad00feb72990 · outbound

This paper cites SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.037855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e323b67-a3a5-4f00-8147-fb9c49f22aaf · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.045767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e100f529-09be-4e20-a5eb-d28a8634ab3c · outbound

This paper cites Scaling Laws for Neural Language Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Scaling Laws for Neural Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.051565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2866c53-62d8-456d-a9f8-b25ad9030b0c · outbound

This paper cites Mahoney, Amir Gholami, and Kurt Keutzer.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Mahoney, Amir Gholami, and Kurt Keutzer

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:57:57.376142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 42dbfc94-e47f-4b83-b8d5-660422c1e317 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.338380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4637c875-57ce-4d38-944f-d835a0c80a81 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.305471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation da7140bc-de6d-4c83-b31f-6610651ff3d1 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.279784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4ce889c9-2c7d-41af-89c2-7c98c93776cc · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.254003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e4718814-3621-4d5c-a825-be5eac159e49 · outbound

This paper cites Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.115574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6689cfae-ed10-4b17-89b6-ea743ce6ff81 · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.137536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6e20e5-c46b-434f-b1d9-ec2c1aa2c301 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.151131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36d669aa-6ba8-410c-8e2b-e453da0267fa · outbound

This paper cites In Proceedings of the 29th ACM Interna- tional Conference on Architectural Support for Programming Languages and Operat- ing Systems, Volume 3 (ASPLOS ’24).

Automatic Task Detection and Heterogeneous LLM Speculative Decoding In Proceedings of the 29th ACM Interna- tional Conference on Architectural Support for Programming Languages and Operat- ing Systems, Volume 3 (ASPLOS ’24)

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.144292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a66620-7e66-4f45-81e2-d58987c54d1c · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.211335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2318b321-9a5b-4cf8-8917-84dad26c8849 · outbound

This paper cites Accelerating LLM Inference with Staged Speculative Decoding.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Accelerating LLM Inference with Staged Speculative Decoding

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.158037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b56ec1b-f439-4e4e-bca2-7cff973664ba · outbound

This paper cites LoRA Meets Dropout under a Unified Framework.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding LoRA Meets Dropout under a Unified Framework

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.184689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdd380dc-05aa-48eb-a548-52070866719a · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.171023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f392512-3f93-459d-94a8-510b05d9ea67 · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.200560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 507d846e-6fc4-446a-98a9-cad00251eaad · outbound

This paper cites Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.193176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0762e50d-ebe1-4fd5-a19c-5ca5a8a62c9a · outbound

This paper cites Inference with Reference: Lossless Acceleration of Large Language Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Inference with Reference: Lossless Acceleration of Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.217782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36515239-0456-4a9a-9fac-fcb11c1644af · outbound

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

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.209797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 948327e4-2878-4331-937f-6c0f9abda58f · outbound

This paper cites Recurrent Drafter for Fast Speculative Decoding in Large Language Models.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.230937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e39801-832f-4858-8c11-e264e8ab6df2 · outbound

This paper cites Scaling Vision Transformers.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Scaling Vision Transformers

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.225118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4087620-f569-4b80-9878-6080d197822c · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.244668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce824fde-1cfb-430f-915d-6c0c2cec4753 · outbound

This paper cites ChemLLM: A Chemical Large Language Model.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding ChemLLM: A Chemical Large Language Model

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.237812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d53802a-0053-468e-98f3-ec044166e59a · outbound

This paper cites an unresolved cited work.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:57:57.179538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7b576094-5321-4ee9-8318-0475139b2a00 · outbound

This paper cites DistillSpec: Improving Speculative Decoding via Knowledge Distillation.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.257387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed68986a-02e5-492e-8071-0f6f110ce841 · outbound

This paper cites Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting.

Automatic Task Detection and Heterogeneous LLM Speculative Decoding Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T21:57:56.100297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.