Paper Citation Record · LEDGER

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks

As of 9 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2608.05926.

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

pith.paper-citation-record.v1
2608.05926 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T21:08:29.373276Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

42 of 42 outbound references displayed

verified exact1
verified fuzzy35
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c202ef84-78f1-4943-a2e3-11d1a0c9782e · outbound

This paper cites Network edge inference for large language models: Principles, tech- niques, and opportunities,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Network edge inference for large language models: Principles, tech- niques, and opportunities,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.758685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d6c3391c-1730-4aa5-908c-a240e1b120bd · outbound

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

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Mobile edge intelligence for large language models: A contemporary survey,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:28.795653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a10b5d-40b2-47ef-90fe-de6d2a5250d7 · outbound

This paper cites QLLMS: Quantization-adaptive LLM scheduling for partially informed edge serving systems,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks QLLMS: Quantization-adaptive LLM scheduling for partially informed edge serving systems,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.738892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5a8c2aa9-c611-4ebf-a8d1-998cbf64e85f · outbound

This paper cites Edge-first language model inference: Models, metrics, and tradeoffs,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Edge-first language model inference: Models, metrics, and tradeoffs,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.725473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cd1f003d-cd3c-44cf-8a2e-affafaac8752 · outbound

This paper cites Large language model partitioning for low-latency inference at the edge,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Large language model partitioning for low-latency inference at the edge,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.713787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4999c787-a28b-4856-8ecc-af4023438ea7 · outbound

This paper cites Taming throughput-latency tradeoff in LLM inference with sarathi-serve,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Taming throughput-latency tradeoff in LLM inference with sarathi-serve,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.702428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 971b823c-a4ed-4ebd-9550-78d6288f56a3 · outbound

This paper cites Attention is all you need,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Attention is all you need,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.692096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad6a93fb-e0fc-479f-b5d2-4756cc183b94 · outbound

This paper cites FFN-SkipLLM: A hidden gem for autoregressive decoding with adap- tive feed forward skipping,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks FFN-SkipLLM: A hidden gem for autoregressive decoding with adap- tive feed forward skipping,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.681807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8d1d594a-a920-4824-8d9d-10610310cbf4 · outbound

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

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.605619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ecf288db-331f-471f-b50d-a58bd58f8eb1 · outbound

This paper cites A theoretical perspective for speculative decoding algorithm,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks A theoretical perspective for speculative decoding algorithm,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.426342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1d86221b-1984-44a9-a752-9fe10e00eda3 · outbound

This paper cites Decoding speculative decoding,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Decoding speculative decoding,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.254424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0a891704-32d6-41f2-be5c-f64955cfa642 · outbound

This paper cites SpecExec: Massively parallel speculative decoding for interactive LLM inference on consumer devices,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks SpecExec: Massively parallel speculative decoding for interactive LLM inference on consumer devices,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.088489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2f22cde4-9768-4b03-bbce-2dfe8496cde1 · outbound

This paper cites QuantSpec: Self-speculative decoding with hierarchical quantized KV cache,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks QuantSpec: Self-speculative decoding with hierarchical quantized KV cache,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.076711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2f627ff2-c25d-4bf5-9c61-f84244227c57 · outbound

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

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Draft & verify: Lossless large language model acceleration via self- speculative decoding,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.065507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b0a088f0-c9ba-4b7e-9bd8-d0908ef97809 · outbound

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

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks SWIFT: On-the-fly self- speculative decoding for LLM inference acceleration,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.052967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fef51e62-a032-4e9e-ba78-f8b0fd24be31 · outbound

This paper cites Edge inference for large language models with pipeline parallelism and batching,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Edge inference for large language models with pipeline parallelism and batching,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.042137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c0f52df3-d546-4693-b3f5-a4abe2801dbd · outbound

This paper cites Beyond the cloud: Edge inference for generative large language models in wireless networks,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Beyond the cloud: Edge inference for generative large language models in wireless networks,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.030415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a776d1f0-696e-46b3-b67d-02d3cd7f8e6d · outbound

This paper cites Resource allocation in large language model integrated 6G vehicular networks,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Resource allocation in large language model integrated 6G vehicular networks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.017703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bfaf85cd-bd5a-4d07-9531-9cba43f57d18 · outbound

This paper cites Communication- efficient distributed on-device LLM inference over wireless networks,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Communication- efficient distributed on-device LLM inference over wireless networks,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:31.002970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fdb8c11f-99d6-4ed6-a2c1-61e9763ded5f · outbound

This paper cites Efficient LLM inference over heterogeneous edge networks with speculative decoding,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Efficient LLM inference over heterogeneous edge networks with speculative decoding,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:29.157535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e869023-8674-42ad-82c1-70f9401efec0 · outbound

This paper cites DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T21:08:29.622307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 29a1d9fe-8c02-4aad-b515-66088ad6d2b3 · outbound

This paper cites SLED: A speculative LLM decoding framework for efficient edge serving,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks SLED: A speculative LLM decoding framework for efficient edge serving,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.738637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 23faed8f-64be-4649-8f59-613d9a2cba5e · outbound

This paper cites OPT-tree: Speculative decoding with adaptive draft tree structure,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks OPT-tree: Speculative decoding with adaptive draft tree structure,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.362101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f309469c-702e-46f2-b5ba-071f3bc3ce91 · outbound

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

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks PEARL: Parallel speculative decoding with adaptive draft length,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.273514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad212f60-cfbb-42e4-acc2-f4e81e6c680d · outbound

This paper cites Think fast, infer smart: A hybrid distributed LLMs inference at the wireless edge,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Think fast, infer smart: A hybrid distributed LLMs inference at the wireless edge,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.259737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a38dc186-7ffc-4731-8ec5-923370845313 · outbound

This paper cites Hybrid LLM: Cost-efficient and quality-aware query routing,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Hybrid LLM: Cost-efficient and quality-aware query routing,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.248779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b5efa405-d9ae-48bf-8553-39b6d315ee1c · outbound

This paper cites Communication-efficient hybrid language model via uncertainty-aware opportunistic and compressed transmission,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Communication-efficient hybrid language model via uncertainty-aware opportunistic and compressed transmission,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.235018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 65d5aa5c-6c44-4655-8b74-163e69737c36 · outbound

This paper cites Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:29.233848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9d7529-2100-453c-add3-687ddc8c4b5d · outbound

This paper cites When, what, and how: Rethinking retrieval-enhanced speculative decoding,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks When, what, and how: Rethinking retrieval-enhanced speculative decoding,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:29.289489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0efae99-d930-4d07-88cd-c817724b4999 · outbound

This paper cites ExeGPT: Constraint-aware resource scheduling for LLM inference,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks ExeGPT: Constraint-aware resource scheduling for LLM inference,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.215195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83ab9c14-685b-4568-89ef-0129fb92b1a9 · outbound

This paper cites Efficient interactive LLM serving with proxy model-based sequence length prediction,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Efficient interactive LLM serving with proxy model-based sequence length prediction,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.196856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cafb86ba-eae3-47cb-b39a-031d5d340bbe · outbound

This paper cites Past-future scheduler for LLM serving under SLA guarantees,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Past-future scheduler for LLM serving under SLA guarantees,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.182107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b7dfc47a-5365-4998-b3a3-df0d4c33f36f · outbound

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

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Orca: A distributed serving system for{Transformer-Based}generative models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.169739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4a4aa75f-4553-4e0e-9315-0d1f0d0db32d · outbound

This paper cites ColBERT: Efficient and effective passage search via contextualized late interaction over BERT,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks ColBERT: Efficient and effective passage search via contextualized late interaction over BERT,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.157573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 762ff0ba-3ecb-4071-a3ec-1fa10c38d1f1 · outbound

This paper cites Reference API.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Reference API

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:30.015890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7f6b3f8f-684b-4884-b6c3-9697451d062d · outbound

This paper cites FlexGen: High-throughput generative inference of large language models with a single GPU,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks FlexGen: High-throughput generative inference of large language models with a single GPU,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:29.844275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e42b014f-0455-4f9f-9b86-c226b759e749 · outbound

This paper cites NVIDIA multi-instance GPU user guide release r580,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks NVIDIA multi-instance GPU user guide release r580,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:29.832168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 05887f2f-7741-45dc-a7ca-2b527abea792 · outbound

This paper cites iGniter: Interference-aware GPU resource provisioning for predictable DNN inference in the cloud,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks iGniter: Interference-aware GPU resource provisioning for predictable DNN inference in the cloud,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:29.349710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d8f6ebe-c30e-4524-93a8-11c4046618ea · outbound

This paper cites Multiuser co- inference with batch processing capable edge server,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Multiuser co- inference with batch processing capable edge server,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T21:08:29.353171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e248ce9e-28ff-4585-8a40-67381b635403 · outbound

This paper cites A fast and scal- able multidimensional multiple-choice knapsack heuristic,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks A fast and scal- able multidimensional multiple-choice knapsack heuristic,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:29.793311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a201f439-1ead-4958-9d96-5ad738dc8e6d · outbound

This paper cites Heuristic algorithms for the multiple-choice multidimensional knapsack problem,.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Heuristic algorithms for the multiple-choice multidimensional knapsack problem,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:29.781164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ab4d71cd-9c34-466c-9a0f-11d0f1c4aced · outbound

This paper cites Available: https://docs.nvidia.com/datacenter/tesla/pdf/ MIG User Guide.pdf.

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks Available: https://docs.nvidia.com/datacenter/tesla/pdf/ MIG User Guide.pdf

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T21:08:29.819444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.