Paper Citation Record · LEDGER

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference

As of 19 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 2 inbound Pith citation observations for arXiv:2412.18934.

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

pith.paper-citation-record.v1
2412.18934 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:24:35.981169Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:16:42.476185Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T10:27:57.145850Z

Reference resolution

49 of 49 outbound references displayed

verified exact2
verified fuzzy2
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 000dfd45-a279-4fd2-9113-d812c4d5e312 · outbound

This paper cites GPT-4 Technical Report.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.702293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a701bdfb-0f30-48b1-b21a-427f58e2288c · outbound

This paper cites Thabet, and Jonas Kohler.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Thabet, and Jonas Kohler

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:24:37.062654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e131f4f7-29d6-4416-bb2f-49166f5d0c14 · outbound

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

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Lee, Deming Chen, and Tri Dao

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.714786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24557240-c4b2-40f3-8aae-85fbe60a426d · outbound

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

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Accelerating Large Language Model Decoding with Speculative Sampling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.723852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932ba29f-5093-4ad4-a3fa-e4d8fe379b10 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Evaluating Large Language Models Trained on Code

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.731227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34843b8e-8c82-4bff-97f9-ff2eee1cd378 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:37.027731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 575c5942-fa90-46fe-a4f2-d4595f06ca86 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.743276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be0264d-06e4-43cc-8b76-3a4497c0df5a · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.748707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25fb070d-426d-4e2c-b1c9-322133381b7c · outbound

This paper cites The State of Sparsity in Deep Neural Networks.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference The State of Sparsity in Deep Neural Networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.755215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b1f321a-c68a-4c53-bad5-83dc4fbb2508 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:37.001462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d58a0f9-aa71-4c1f-9541-76723e4920a3 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.766386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215c9c68-b17f-49ff-b6dc-1bbf2311268b · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.772007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba1bcf3-20ff-45e5-ac5b-c86505d09123 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.954274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bc0846c9-75a7-450f-8f02-35553e695b29 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.782447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fab4fe5b-f57c-40d6-86fb-266be2f349e9 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.926274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2d1bf239-376e-4312-a18d-0b706abe9682 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.793595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ce776c6-8d92-4b62-a54e-8891acde9ee7 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.803349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b181f5a-3657-46a0-bfcd-428892ae461b · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.880878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7703dc54-683b-4bd9-a1ea-f951a7438039 · outbound

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

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.815578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc16fb34-d3a1-4204-8bca-a4ee50a724ab · outbound

This paper cites Gonz \' a lez.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Gonz \' a lez

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:24:36.860180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c459adf-d4fa-43d1-af0a-cd23201d2412 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.827661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb2c3271-956d-43a5-af7a-1f178f766e21 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.829734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0737972c-c3fb-42c7-a6ec-5a95f28763d6 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.840451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bcabb1c-4178-49af-af46-0b433b307f07 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.845856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd39a8a-bfcd-4254-9f23-681d46c1caf7 · outbound

This paper cites Accelerating LLM Inference with Staged Speculative Decoding.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Accelerating LLM Inference with Staged Speculative Decoding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.853031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7568c8c8-f185-4ee0-be83-6a1b558554f6 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.810658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f1b39706-09b6-4883-b1d3-881a19e0017d · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.792305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 290ddd5c-0b5b-4f42-aeb3-027d4c5250ac · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.764434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 137dbdb1-35de-4bba-a2bc-adef1e2c02d6 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.877105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3374eb9-b9f1-4393-afbc-bcfec89e7288 · outbound

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

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference LLaMA: Open and Efficient Foundation Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.881716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f8eca9e-da26-426e-a6f1-247511d17554 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 31

Resolution: verified exact; doi, observed 2026-08-11T04:24:36.103768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7a77ccc8-3cee-4a02-b3b1-4f5110958483 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.891570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5c208a-337a-40f0-a501-12f42d9b3ce2 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.896627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3b866b-f3f3-42ac-9554-528d21d6a627 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.901969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e53070-d52c-4e7d-8944-4036caadcbc8 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.907085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5003c02c-1199-45a5-9c0e-82bb25a1b57d · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.718851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2d0c31df-27a7-4fd0-b93c-0c2e05fe7d7a · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.917530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b4f99b1-608e-4fbe-bc94-afeff6633f09 · outbound

This paper cites Decoding Speculative Decoding.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Decoding Speculative Decoding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.922407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec4a10f-2931-4168-9c4b-cf65530c9f52 · outbound

This paper cites Qwen2 Technical Report.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Qwen2 Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.928411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cf9f0a6-41d7-4dce-a313-510ea9398f55 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.684435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8a255dfb-a960-4e42-a867-ea1ba2b9eac1 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:24:36.665713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 574861c2-9ddd-415e-886f-b6d711a6a856 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 42

Resolution: verified exact; doi, observed 2026-08-11T04:24:36.048664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cf925d96-a0b0-432b-8deb-967adb0b2d8b · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.948863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d921c1b2-d2aa-4282-b5b0-ba9f2176527f · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference TinyLlama: An Open-Source Small Language Model

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.954216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42727c0a-1773-4423-a0b9-c7e8d5583029 · outbound

This paper cites an unresolved cited work.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.960317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc2c4473-0d33-452c-a2b4-d23db04c7cb6 · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference Xing, Hao Zhang, Joseph E

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.965209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510fd849-a333-4fc4-9760-abf6eed869f3 · outbound

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

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.970411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c85abd-f13e-4e38-9fd9-9e3d7131ebe3 · outbound

This paper cites online" 'onlinestring :=.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference online" 'onlinestring :=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.975492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ff95603-5e93-4520-b17d-bac419add9b7 · outbound

This paper cites write newline.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference write newline

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T04:24:35.981169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 32ac6e75-29cb-4ae5-8a7b-7d439bd44850 · inbound

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization cites this paper.

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:42.476185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1c6e089-7110-44c5-8400-2fd14bf0e2ab · inbound

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion cites this paper.

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:27:57.147259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.