Paper Citation Record · LEDGER

Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 8 inbound Pith citation observations for arXiv:2505.04519.

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

pith.paper-citation-record.v1
2505.04519 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:51:53.375231Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T04:35:20.955614Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 2796a3e0-6168-466b-9bdb-8b380bb04e78 · inbound

Serving Large Language Models on Huawei CloudMatrix384 cites this paper.

Serving Large Language Models on Huawei CloudMatrix384 Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:53.375231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f6c0f8a-4699-4356-87fc-ea4dc9ce2766 · inbound

DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training cites this paper.

DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T16:21:33.256198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5261ea6-e128-4abd-9d2c-0c1430b02128 · inbound

Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs cites this paper.

Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:36:17.238231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d70dfcac-ca69-476f-8926-05720f1d8ea5 · inbound

MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems cites this paper.

MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:46:20.566120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bb9c390-7dee-40a2-991c-7c9e03ba1aab · inbound

Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing cites this paper.

Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:41:11.017629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 35730974-296d-460b-b102-2a821925f719 · inbound

Hierarchical Mixture-of-Experts with Two-Stage Optimization cites this paper.

Hierarchical Mixture-of-Experts with Two-Stage Optimization Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:46:26.787283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b45019b8-f3e0-4bb0-bc03-b5a0b2d981b9 · inbound

Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models cites this paper.

Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:35:20.958362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d81f2810-8add-4ec2-a570-05afc2d10f0a · inbound

MoX: Efficient MoE Routing on Direct-Connect Topologies cites this paper.

MoX: Efficient MoE Routing on Direct-Connect Topologies Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T10:29:59.857176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.