Paper Citation Record · LEDGER

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving

As of 5 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2605.00831.

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

pith.paper-citation-record.v1
2605.00831 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-15T00:37:08.671539Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

24 of 24 outbound references displayed

verified exact15
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1f32c318-668d-4544-9bcd-c918306c2685 · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 40cf2f55-f826-430b-b478-0bb215411241 · outbound

This paper cites 2025.No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving 2025.No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.090087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f336952-cfe7-480a-9cf2-fc50bb54a60a · outbound

This paper cites K., Janakiraman, R., and Xu, L.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving K., Janakiraman, R., and Xu, L

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T00:38:23.691453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f189bdce-0ca6-4c60-a276-1464c4d55027 · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T00:38:23.693289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 03632557-c26b-4c89-a771-071cdba79daf · outbound

This paper cites LithOS: An Operating System for Efficient Machine Learning on GPUs.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving LithOS: An Operating System for Efficient Machine Learning on GPUs

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.080048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ba6c971b-44b2-4d65-9383-188482e59c92 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-15T00:38:23.086652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7fbb0742-452e-4d74-a18e-27b87f258025 · outbound

This paper cites G., and Yang, J.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving G., and Yang, J

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T00:38:23.695085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5e329564-c35a-48a8-a297-97cca508cf6b · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T00:38:23.137446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5f1a7cbd-251c-4db1-9a9d-330552fe9476 · outbound

This paper cites Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-15T00:38:23.083416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1115cdd8-ca82-4100-bfc7-8462b890676d · outbound

This paper cites Training Compute-Optimal Large Language Models.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Training Compute-Optimal Large Language Models

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T00:38:23.114487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 50cd5564-0d7d-473b-9401-79f63bd87680 · outbound

This paper cites Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.108123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bb503c89-5bcb-4c9e-91b2-9976bb34ac6f · outbound

This paper cites Scaling Laws for Neural Language Models.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Scaling Laws for Neural Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-15T00:38:23.100128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7221dabb-4205-4175-9750-75eb80846d88 · outbound

This paper cites Revisiting reliability in large-scale machine learning research clusters.2025 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Revisiting reliability in large-scale machine learning research clusters.2025 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T00:38:23.687864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d3ff529d-b3d9-46e5-8ea7-b8a05c71a8b9 · outbound

This paper cites Understanding Stragglers in Large Model Training Using What-if Analysis.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Understanding Stragglers in Large Model Training Using What-if Analysis

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.118021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 889ee8a7-05b6-4da5-8069-68d56240f472 · outbound

This paper cites Enhancing relia- bility in ai inference services: An empirical study on real production incidents.ArXiv, abs/2511.07424.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Enhancing relia- bility in ai inference services: An empirical study on real production incidents.ArXiv, abs/2511.07424

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.104043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1283926b-249c-4c8a-a9d8-13a88c0ba556 · outbound

This paper cites Salpekar, R.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Salpekar, R

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T00:38:23.077148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3d6f1dc7-4be7-4ede-a732-8a8f007b9148 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-15T00:38:23.130518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 854b60c6-4938-49f3-a83d-f527498fb772 · outbound

This paper cites 2024 crowdstrike-related it outages.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving 2024 crowdstrike-related it outages

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T00:38:23.689769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e9d8b662-e73d-445e-86ed-15b90c7c7276 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-15T00:38:23.127082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1da15145-5a79-40c6-a3ca-a2837908f483 · outbound

This paper cites Fast Distributed Inference Serving for Large Language Models.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Fast Distributed Inference Serving for Large Language Models

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:23:46.844514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5af68555-97f5-4986-ad77-b6ede239c494 · outbound

This paper cites Context Parallelism for Scalable Million-Token Inference.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Context Parallelism for Scalable Million-Token Inference

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T00:38:23.124324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bffeda50-3fa6-4530-b5be-a9295d55c3e5 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-16T13:26:34.840430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6f8048e6-cdaa-4392-ac5a-1e1291b86f2a · outbound

This paper cites ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.111335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fd98a068-3906-4903-9d7c-a58fd7ffb68b · outbound

This paper cites SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:38:23.097181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.