Paper Citation Record · LEDGER

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks

As of 14 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2608.04974.

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

pith.paper-citation-record.v1
2608.04974 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:36:19.912415Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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

37 of 37 outbound references displayed

verified exact2
verified fuzzy14
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4abca992-c557-4037-94e4-b5ecdc3210d0 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks LaMDA: Language Models for Dialog Applications

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.022804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76ac4c14-d05a-4d7f-bb88-ce28039d7af2 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Evaluating Large Language Models Trained on Code

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.075148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 094b3ea1-7b1b-4432-a548-3d7ea802b001 · outbound

This paper cites Language models are few-shot learners,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Language models are few-shot learners,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.294524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d7f61f67-4ba0-498d-8a37-7b91d43461cf · outbound

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

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Chain-of-thought prompting elicits reasoning in large language models,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.228799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2868cd6-26e6-4e27-a8a1-c19c908c59c3 · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks ReAct: Synergizing reasoning and acting in language models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.261964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c5bd3f09-50e3-46a1-a499-9cdb7cbdb9c8 · outbound

This paper cites Fast inference from transform- ers via speculative decoding,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Fast inference from transform- ers via speculative decoding,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.243578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0bed100a-8ffb-4e10-af62-61455f33b500 · outbound

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

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Accelerating Large Language Model Decoding with Speculative Sampling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.473974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3882188b-0fda-4c61-a2bf-692a96cbc249 · outbound

This paper cites DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.592235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3dc7e1e-40e9-428c-adff-7f5eae568e78 · outbound

This paper cites SpecEdge: Scalable edge-assisted serving framework for interactive LLMs,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks SpecEdge: Scalable edge-assisted serving framework for interactive LLMs,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.613009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29417c33-f66f-4647-b731-c3b27e2231dd · outbound

This paper cites PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.698765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c9434f-3656-4483-9444-3e717a135414 · outbound

This paper cites Communication-efficient collaborative LLM inference via distributed speculative decoding,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Communication-efficient collaborative LLM inference via distributed speculative decoding,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.764588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f0231c-6d03-4eae-af2c-576218c9eb37 · outbound

This paper cites Fast collaborative inference via distributed speculative decoding,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Fast collaborative inference via distributed speculative decoding,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.820864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d36d676-f2bc-4dd7-83b7-49ab960c675c · outbound

This paper cites Speculation at a Distance: Where Edge-Cloud Speculative Decoding Actually Pays Off.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Speculation at a Distance: Where Edge-Cloud Speculative Decoding Actually Pays Off

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-06T12:36:20.698329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7803a98a-0f7d-4895-b61c-0ebdf468abeb · outbound

This paper cites LLMCad: Fast and Scalable On-device Large Language Model Inference.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks LLMCad: Fast and Scalable On-device Large Language Model Inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:18.965771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4756b5c1-76b0-41f7-9c6b-5df33728aad3 · outbound

This paper cites PipeInfer: Accelerating LLM inference using asynchronous pipelined speculation,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks PipeInfer: Accelerating LLM inference using asynchronous pipelined speculation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.225678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5317e4c7-af90-4f9f-9723-cb26b2763491 · outbound

This paper cites AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-06T12:36:20.655192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0f91947f-9f3b-4704-a4f2-5c78a3cfc602 · outbound

This paper cites PEARL: Parallel Speculative Decoding with Adaptive Draft Length.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.142900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ffcbad-81ac-4327-afd6-dfd0eaf6e471 · outbound

This paper cites CoSine: Enhancing LLM serving via collaborative and decoupled speculative inference,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks CoSine: Enhancing LLM serving via collaborative and decoupled speculative inference,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.209820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2e4dcc7b-a326-494b-b78b-a271e1f1eb7d · outbound

This paper cites WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.307246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02334612-7cf9-4ad2-8318-e08e5c5458c2 · outbound

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

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Efficient memory management for large language model serving with PagedAttention,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.195343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ec503571-a30b-443f-90ca-cea55c7dfc5b · outbound

This paper cites DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.177676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d69efdaf-1f98-4cea-9110-35ed0e022303 · outbound

This paper cites Hintjens,ZeroMQ: Messaging for Many Applications.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Hintjens,ZeroMQ: Messaging for Many Applications

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.160747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5283f376-d789-4feb-9e0d-1503c5616673 · outbound

This paper cites Qwen3 Technical Report.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Qwen3 Technical Report

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.653286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1d515f-886d-4201-9050-fa36e1c54c1f · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.780905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae5f4fff-3cf4-4b06-a654-810235f69f6a · outbound

This paper cites GLM-4-0414 model series,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks GLM-4-0414 model series,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.143920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 24e9ffe7-09bb-4376-b798-19fa828f2a4a · outbound

This paper cites The Llama 3 Herd of Models.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks The Llama 3 Herd of Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.863122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 024c70b3-fe2b-4f9c-b370-93dd627a7ef3 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Training Verifiers to Solve Math Word Problems

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.867867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ba4cc5-d4bb-4acd-853a-fdcae6da06db · outbound

This paper cites Network emulation with NetEm,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Network emulation with NetEm,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.125916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 79db0f21-fc59-4108-a3c3-a494a5fc772f · outbound

This paper cites Understanding operational 5G: A first measurement study on its coverage, performance and energy consumption,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Understanding operational 5G: A first measurement study on its coverage, performance and energy consumption,

Reference 29

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T12:36:20.517187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0eaae0b7-6455-49db-ab51-ad99b27070dc · outbound

This paper cites AccuMO: Accuracy- centric multitask offloading in edge-assisted mobile augmented reality,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks AccuMO: Accuracy- centric multitask offloading in edge-assisted mobile augmented reality,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.108775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 56922e96-a8a1-42f6-8f67-5b41aa1e31c4 · outbound

This paper cites A variegated look at 5G in the wild: Performance, power, and QoE implications,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks A variegated look at 5G in the wild: Performance, power, and QoE implications,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.886247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43331e2d-b63c-4062-8ec1-3e4dadd27321 · outbound

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

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks SpecInfer: Accelerating large language model serving with tree-based speculative inference and verification,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.087597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ed46086d-f049-4d37-bdd6-73f221525c1c · outbound

This paper cites Medusa: Simple LLM inference acceleration framework with multiple decoding heads,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Medusa: Simple LLM inference acceleration framework with multiple decoding heads,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.064875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation efa1ef77-0fb2-48ac-89d2-8614997cad04 · outbound

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

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.898830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c7deeb8-c10c-492d-a554-e08f6192cd1e · outbound

This paper cites Conformal sparsification for bandwidth-efficient edge-cloud speculative decoding,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Conformal sparsification for bandwidth-efficient edge-cloud speculative decoding,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.903391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e9a913-8c70-49fa-bc55-83f5984496bf · outbound

This paper cites Quantize- sample-and-verify: LLM acceleration via adaptive edge-cloud speculative decoding,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Quantize- sample-and-verify: LLM acceleration via adaptive edge-cloud speculative decoding,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T12:36:19.907751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4253d224-9c9d-4097-b566-1200d8643893 · outbound

This paper cites Taming throughput-latency tradeoff in LLM inference with Sarathi-Serve,.

AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks Taming throughput-latency tradeoff in LLM inference with Sarathi-Serve,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:36:21.044466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

No inbound Pith citation observations are available.