Paper Citation Record · LEDGER

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving

As of 18 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2606.17787.

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

pith.paper-citation-record.v1
2606.17787 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T22:53:58.352008Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

45 of 45 outbound references displayed

verified exact5
verified fuzzy0
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a50ef0c8-068d-4fa3-9305-9fbaff6a797e · outbound

This paper cites https:// docs.vllm.ai/en/stable/deployment/k8s/, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https:// docs.vllm.ai/en/stable/deployment/k8s/, 2026

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df5d1cf0-a1c7-4c6d-b9b1-43563d9ff6c8 · outbound

This paper cites https: //github.com/flashinfer-ai/flashinfer, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https: //github.com/flashinfer-ai/flashinfer, 2026

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eec8535-1c49-4233-8c49-e7445cde2f5c · outbound

This paper cites an unresolved cited work.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acf3725c-eac4-47f5-94b1-c5d9e7be79c4 · outbound

This paper cites https: //huggingface.co/docs/text-generation- inference, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https: //huggingface.co/docs/text-generation- inference, 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 701ca8b4-f9b7-4b55-8585-2de165840038 · outbound

This paper cites https://github.com/kserve/kserve, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https://github.com/kserve/kserve, 2026

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23f45e03-73f7-413e-a239-e7085c7510c8 · outbound

This paper cites https: //github.com/triton-inference-server/server, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https: //github.com/triton-inference-server/server, 2026

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4695858-47cc-434c-a8e0-c99a4a748883 · outbound

This paper cites https://pytorch.org, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https://pytorch.org, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afd8ff5c-6475-49f8-9b2f-9e36f1cd873e · outbound

This paper cites https://zeromq.org, 2026.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving https://zeromq.org, 2026

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b713c946-798f-4d39-aad2-cdf79a4cd3a1 · outbound

This paper cites Vidur: A large-scale simulation framework for LLM inference.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Vidur: A large-scale simulation framework for LLM inference

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4fbf55-0dfd-4729-8e6a-f573a0dda2e6 · outbound

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

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Taming throughput- latency tradeoff in LLM inference with Sarathi-Serve

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f6ed29-fa9a-4e33-98c0-5ede73efd04a · outbound

This paper cites an unresolved cited work.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98d1a7b1-350b-44ed-9c07-be3785c4ef8b · outbound

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

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Accelerating Large Language Model Decoding with Speculative Sampling

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-03T23:09:01.189168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d98aca0-3450-4bb5-8e64-ca52f26e3ecd · outbound

This paper cites Recycle: Resilient training of large DNNs using pipeline adaptation.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Recycle: Resilient training of large DNNs using pipeline adaptation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94ea7503-a455-4be8-9f72-d01228cb1099 · outbound

This paper cites Cost-efficient large language model serving for multi-turn conversations with CachedAtten- tion.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Cost-efficient large language model serving for multi-turn conversations with CachedAtten- tion

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a747b482-a093-44e9-b235-fc9c34e81dfb · outbound

This paper cites Characterization of large language model devel- opment in the datacenter.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Characterization of large language model devel- opment in the datacenter

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56d1b946-fa90-4ad8-ad8f-bfb6e3f6d005 · outbound

This paper cites Oobleck: Resilient distributed training of large models using pipeline templates.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Oobleck: Resilient distributed training of large models using pipeline templates

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 515ecadb-84bc-437c-8c44-7a9e3072bdeb · outbound

This paper cites GhostServe: A lightweight checkpointing system in the shadow for fault-tolerant LLM serving.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving GhostServe: A lightweight checkpointing system in the shadow for fault-tolerant LLM serving

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95689ca0-8f85-440a-8936-2ef05fadd90c · outbound

This paper cites MegaScale: Scaling large language model training to more than 10,000 GPUs.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving MegaScale: Scaling large language model training to more than 10,000 GPUs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed395e94-2832-470a-ad0d-f0f5027ebac4 · outbound

This paper cites Revisiting reliability in large-scale machine learning research clusters.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Revisiting reliability in large-scale machine learning research clusters

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bc8901c-819e-41fb-ba2a-8d082e8e96a7 · outbound

This paper cites Efficient memory man- agement for large language model serving with Page- dAttention.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Efficient memory man- agement for large language model serving with Page- dAttention

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5175a2b5-3a68-4f8b-8a1d-cfa9fdadb63e · outbound

This paper cites Fast inference from transformers via speculative decoding.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Fast inference from transformers via speculative decoding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation added2ae-d8c7-463b-9ed1-25ef75b9edc5 · outbound

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

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving PEARL: Parallel speculative decoding with adaptive draft length

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb39cfe3-cd5f-4adb-87eb-ef22e76cc1ee · outbound

This paper cites CacheGen: KV cache compression and streaming for fast large language model serving.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving CacheGen: KV cache compression and streaming for fast large language model serving

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bac4c3d-c534-47ac-855a-ef8d24467246 · outbound

This paper cites The Llama 3 Herd of Models.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving The Llama 3 Herd of Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-03T23:09:01.186199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dba359e2-87a3-45fd-a6a3-4205127ea8ab · outbound

This paper cites AMUSD: Asynchronous multi- device speculative decoding for LLM acceleration.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving AMUSD: Asynchronous multi- device speculative decoding for LLM acceleration

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f31f6144-a051-47f3-a1be-f18954711ad6 · outbound

This paper cites Splitwise: Efficient generative LLM inference using phase splitting.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Splitwise: Efficient generative LLM inference using phase splitting

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19009165-96f7-46d6-9df1-04dc08ef38c7 · outbound

This paper cites ECCheck: Enhancing in-memory check- point with erasure coding in distributed DNN training.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving ECCheck: Enhancing in-memory check- point with erasure coding in distributed DNN training

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ad37d1b-49c6-43b4-a423-a497bfc98a1b · outbound

This paper cites Towards resiliency in large language model serving with KevlarFlow.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Towards resiliency in large language model serving with KevlarFlow

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-03T23:09:01.193291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 153437a6-363a-4fe3-88a0-09f5421cd3e1 · outbound

This paper cites Mooncake: Trading more storage for less computation – a KVCache-centric architecture for serving LLM chat- bot.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Mooncake: Trading more storage for less computation – a KVCache-centric architecture for serving LLM chat- bot

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 360ecb2f-7a53-46a8-aebe-021cd4b73805 · outbound

This paper cites ShareGPT conversation dataset.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving ShareGPT conversation dataset

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fc473c8-2533-4ddb-9c19-f87ba7c755f4 · outbound

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

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving FlexGen: High- throughput generative inference of large language mod- els with a single GPU

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0befe7a2-ac5b-4a55-a9cc-07357fb3f436 · outbound

This paper cites DéjàVu: KV-cache streaming for fast, fault-tolerant generative LLM serv- ing.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving DéjàVu: KV-cache streaming for fast, fault-tolerant generative LLM serv- ing

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94d765e1-aebf-4d92-b496-5c9e849f8c99 · outbound

This paper cites Llumnix: Dy- namic scheduling for large language model serving.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Llumnix: Dy- namic scheduling for large language model serving

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb7d7f18-bf5b-48ad-b556-301b453006ff · outbound

This paper cites Bamboo: Making preemptible in- stances resilient for affordable training of large DNNs.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Bamboo: Making preemptible in- stances resilient for affordable training of large DNNs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e352b913-5f7a-4493-8a1f-644d3e34d3d3 · outbound

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

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-03T23:09:01.195699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 60346195-0523-4335-bf39-8b4459dc9add · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b86e601-9fd8-484d-879f-9d759b9a2487 · outbound

This paper cites ByteCheckpoint: A unified checkpointing system for large foundation model development.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving ByteCheckpoint: A unified checkpointing system for large foundation model development

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 767c681d-bcb1-4ac1-aa04-ad2c3c248818 · outbound

This paper cites an unresolved cited work.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d92a333d-db58-44b8-a9e6-6bed58a0a42a · outbound

This paper cites Fast distributed inference serving for large language models.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Fast distributed inference serving for large language models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d92c734-89a3-4b37-8d4f-b355a1466328 · outbound

This paper cites FailSafe: High-performance resilient serv- ing.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving FailSafe: High-performance resilient serv- ing

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 132556ef-0f08-4109-b294-bf595c950621 · outbound

This paper cites Qwen3 Technical Report.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Qwen3 Technical Report

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-03T23:09:01.191928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 147a22fe-75dd-4747-8ed3-2c5113223e8e · outbound

This paper cites Orca: A distributed serving system for transformer-based generative models.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Orca: A distributed serving system for transformer-based generative models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c57243e-6044-475c-a09e-84826308776b · outbound

This paper cites Gonzalez, Clark Bar- rett, and Ying Sheng.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Gonzalez, Clark Bar- rett, and Ying Sheng

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2349f40-b36b-4963-bab5-575d3f837a11 · outbound

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

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Dist- Serve: Disaggregating prefill and decoding for goodput- optimized large language model serving

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 650d2676-44dd-4bc8-8308-af8833cd27e8 · outbound

This paper cites Resiliency at scale: Managing Google’s TPUv4 machine learning supercomputer.

LUMEN: Coordinated Failure Recovery for Distributed LLM Serving Resiliency at scale: Managing Google’s TPUv4 machine learning supercomputer

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-26T22:53:58.352008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.