Paper Citation Record · LEDGER

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices

As of 14 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 3 inbound Pith citation observations for arXiv:2508.17137.

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

pith.paper-citation-record.v1
2508.17137 v1

Coverage vector

measured 6 of 6 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:03:43.271140Z

measured 9 of 9 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:43:19.327779Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T00:48:39.291244Z

Reference resolution

6 of 6 outbound references displayed

verified exact0
verified fuzzy3
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 94c46255-a666-451d-b290-ce5b4aa13816 · outbound

This paper cites MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache.

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:03:42.658889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8bfb265-4748-4fe9-9caa-a729f3db85ad · outbound

This paper cites DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale.

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T17:03:42.700380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea7b1f7-3275-4444-99dc-50cab36ce5fe · outbound

This paper cites Efficient Training of Energy-Based Models Using Jarzynski Equality.

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices Efficient Training of Energy-Based Models Using Jarzynski Equality

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T17:03:43.630924Z

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 57a2d3eb-94ae-493a-bba4-99ac10955884 · outbound

This paper cites https://www.usenix.org/system/files/osdi23-cui.pdf.

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices https://www.usenix.org/system/files/osdi23-cui.pdf

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:03:44.449613Z

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 912e3779-71af-42a4-81a0-2525b4ceb2a2 · outbound

This paper cites Puffin Dataset.

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices Puffin Dataset

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:03:44.226368Z

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 848a8326-e4d8-46d0-9d83-0b317bff50a6 · outbound

This paper cites WebGLM-QA Dataset.

MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices WebGLM-QA Dataset

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:03:43.931911Z

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

Observation 7ee5e692-27fe-4b8f-b8db-98809f331c61 · inbound

SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models cites this paper.

SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T10:18:55.257434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2d4a0d-f696-45ec-934f-ae7d420e80a3 · inbound

When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes cites this paper.

When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-12T00:48:39.296284Z

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 64bcaffd-bcaf-47d5-9615-522c1318893b · inbound

When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes cites this paper.

When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T04:43:19.327779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.