Paper Citation Record · LEDGER

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference

As of 4 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2604.17701.

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

pith.paper-citation-record.v1
2604.17701 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T04:33:28.537449Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-13T04:55:10.714993Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-13T04:57:17.484903Z

Reference resolution

39 of 39 outbound references displayed

verified exact14
verified fuzzy24
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ea770806-de10-4962-a52b-f4a69e9bff74 · outbound

This paper cites Mobile edge intelligence for large language models: A contemporary survey.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Mobile edge intelligence for large language models: A contemporary survey

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.538873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 38e8d9a4-982e-4b53-8bd9-53d372914139 · outbound

This paper cites On-Device Language Models: A Comprehensive Review.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference On-Device Language Models: A Comprehensive Review

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.809144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2a5eb973-afd0-4942-bacd-ede152a7e173 · outbound

This paper cites Empowering edge intelligence: A comprehensive survey on on-device ai models.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Empowering edge intelligence: A comprehensive survey on on-device ai models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.542093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 59a89f09-fca0-4e61-89c1-58f7a856ef49 · outbound

This paper cites Empowering large language models to edge intelligence: A survey of edge efficient llms and techniques.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Empowering large language models to edge intelligence: A survey of edge efficient llms and techniques

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.548700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1f910679-a59a-4fca-97b0-c68219b20b88 · outbound

This paper cites Large language models empowered autonomous edge ai for connected intelligence.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Large language models empowered autonomous edge ai for connected intelligence

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.545222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 709615ee-77c4-4de4-b1a6-cf7caacba0b7 · outbound

This paper cites Communication- efficient edge ai: Algorithms and systems.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Communication- efficient edge ai: Algorithms and systems

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.562100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c0f1c348-ce01-41ad-bba4-7991735498e0 · outbound

This paper cites Pushing ai to wireless network edge: An overview on integrated sensing, communication, and computation towards 6g.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Pushing ai to wireless network edge: An overview on integrated sensing, communication, and computation towards 6g

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.565609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 57affa06-e623-4b07-a3bc-1cc3a1a21b11 · outbound

This paper cites Wdmoe: Wireless distributed mixture of experts for large language models.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Wdmoe: Wireless distributed mixture of experts for large language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.552026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 46920aad-79ef-4aad-8fa3-fbc29e63e10f · outbound

This paper cites Petals: Collaborative inference and fine-tuning of large models.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Petals: Collaborative inference and fine-tuning of large models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.555345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b4f58eeb-4a6e-486e-a7c3-202ee508504a · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Fast inference from transform- ers via speculative decoding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.559101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 573d61d9-60ef-40da-acde-d9767dcdd597 · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Accelerating Large Language Model Decoding with Speculative Sampling

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:29:36.391032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 89822042-da79-445d-84ca-99989ad3c577 · outbound

This paper cites Dsd: A distributed speculative decoding solution for edge-cloud agile large model serving.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Dsd: A distributed speculative decoding solution for edge-cloud agile large model serving

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.832651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7de111c9-26ef-4b8d-86ff-ef1f53fbe64b · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.827337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 31f43206-38ff-4b60-bca9-bfde9acff00b · outbound

This paper cites Neurosurgeon: Collaborative intelligence between the cloud and mobile edge.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Neurosurgeon: Collaborative intelligence between the cloud and mobile edge

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.517257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ecbecdc4-5239-4856-9223-3b21290b24f4 · outbound

This paper cites On-demand accelerating deep neural network inference via edge computing.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference On-demand accelerating deep neural network inference via edge computing

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.529703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cfecc28f-8076-4c76-9743-b08593ee4896 · outbound

This paper cites Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.523162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d748febf-634f-421f-a53e-0d9054510e50 · outbound

This paper cites Nestdnn: Resource-aware multi- tenant on-device deep learning for continuous mobile vision.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Nestdnn: Resource-aware multi- tenant on-device deep learning for continuous mobile vision

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.495210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5d831d70-02cf-485c-8c00-4ee0cc6fe5ed · outbound

This paper cites Early-exit deep neural network-a comprehensive survey.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Early-exit deep neural network-a comprehensive survey

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.510010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c85deaaf-518c-45ea-9609-e1ecda05d51a · outbound

This paper cites Split learning for health: Distributed deep learning without sharing raw patient data.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Split learning for health: Distributed deep learning without sharing raw patient data

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.835289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8ea66bec-d4a3-4616-9959-a307d3605a9e · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.830033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a4fc6ae4-7983-4bf3-be56-b3feebc3974c · outbound

This paper cites Evangelos Georganas, Dhiraj D.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Evangelos Georganas, Dhiraj D

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:25:22.813954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c5a5bf05-9b3f-40f6-9a57-5b7a0c6ed6de · outbound

This paper cites Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:25:22.822107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 65fede08-81ee-4548-85fd-01e75a61a095 · outbound

This paper cites Overcoming joint intractability with lossless hierarchical speculative decoding.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Overcoming joint intractability with lossless hierarchical speculative decoding

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.837963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 41c000e5-3a64-407f-bd7a-414718da2606 · outbound

This paper cites Accelerating LLM Inference with Staged Speculative Decoding.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Accelerating LLM Inference with Staged Speculative Decoding

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.811588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cd667de8-3908-43b1-8814-f611aad7c41e · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:36:18.892007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec485b51-a501-49d2-930f-bf2648d3b9c1 · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:15:49.524886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5cfba51d-c1ef-4810-9003-d679447db2ee · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Eagle-2: Faster inference of language models with dynamic draft trees

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.513529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 69db1f5b-f20d-4c64-b800-193dafc7eef4 · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:52:19.804345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6c059532-3c68-417d-864e-eb7d0bd87c2b · outbound

This paper cites Draft& verify: Lossless large language model acceleration via self- speculative decoding.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Draft& verify: Lossless large language model acceleration via self- speculative decoding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.532274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 965f3e71-1d2e-4745-9cc5-24ff67c68801 · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Efficient memory management for large language model serving with pagedattention

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.502595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 36c8d4cb-70c4-4c58-8899-ed82a92f0cd8 · outbound

This paper cites Orca: A distributed serving system for{Transformer-Based}generative models.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Orca: A distributed serving system for{Transformer-Based}generative models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.498750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation eb44aa2d-b841-4a8a-9b0a-d43a6f3cc9c5 · outbound

This paper cites Taming{Throughput-Latency}tradeoff in{LLM}inference with{Sarathi-Serve}.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Taming{Throughput-Latency}tradeoff in{LLM}inference with{Sarathi-Serve}

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.535307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 46f113ec-8280-415b-b45d-61d103517c81 · outbound

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

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference {DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.491820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 88be7130-05a7-448b-8e30-43b6d49fd923 · outbound

This paper cites Efficiently scaling transformer inference.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Efficiently scaling transformer inference

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.488708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ebc6218a-abcf-46f1-be1d-d6a5b82d4c4c · outbound

This paper cites Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.520412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b067d309-02f7-446b-a31c-423daf205418 · outbound

This paper cites Flexgen: High-throughput generative inference of large language models with a single gpu.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Flexgen: High-throughput generative inference of large language models with a single gpu

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.506420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a3670fb3-bc4c-40b1-aaef-bce305e2ba2e · outbound

This paper cites DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:25:22.801633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f4b2d268-2043-4ac0-88c0-c039704b5a73 · outbound

This paper cites Sled: A speculative llm decoding framework for efficient edge serving.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Sled: A speculative llm decoding framework for efficient edge serving

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T04:36:04.526128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 154cb98c-8c0e-487c-a59c-5e7e5a0ccdb2 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Training Verifiers to Solve Math Word Problems

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:25:22.806620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation bb341d7f-f58b-4820-bcbe-7e989432030a · inbound

CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference cites this paper.

CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-13T04:57:17.486628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.