Paper Citation Record · LEDGER

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs

As of 8 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2505.20155.

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

pith.paper-citation-record.v1
2505.20155 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:03:50.230653Z

measured 27 of 27 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

27 of 27 outbound references displayed

verified exact0
verified fuzzy1
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a7bb6bb2-7bfd-4cff-a62f-3df0890ec3b1 · outbound

This paper cites GPT-4 Technical Report.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:45.589327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3875c603-d1fb-44de-9600-88164dad398d · outbound

This paper cites Fluctuation-based adaptive structured pruning for large language models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Fluctuation-based adaptive structured pruning for large language models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:45.813530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f583b216-7d27-41cb-abfb-421b17e8792b · outbound

This paper cites SliceGPT: Compress Large Language Models by Deleting Rows and Columns.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:47.433610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c95d95c-92de-4e67-918a-590c1e80d78e · outbound

This paper cites Layer Normalization.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Layer Normalization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:47.885148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d545edcf-f197-457a-8148-c6806cce1427 · outbound

This paper cites Puzzle: Distillation-Based NAS for Inference-Optimized LLMs.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.003294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab5afdd-292a-42c9-9b4e-bb77f805e6b5 · outbound

This paper cites bert2BERT: Towards Reusable Pretrained Language Models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs bert2BERT: Towards Reusable Pretrained Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.143877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92110032-d165-49ac-8391-e96b0591203c · outbound

This paper cites The Llama 3 Herd of Models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.288660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db65e958-1a6a-4023-a763-90c95870fdd4 · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.413639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512347b6-c9e4-4d31-83f3-b881c26f44bb · outbound

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

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.536521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 679708b8-e580-4377-8e40-2c0a3afc7172 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Distilling the Knowledge in a Neural Network

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.628769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d45a5f1f-9194-4e91-91ef-20498241ab00 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.732655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10dcde56-a951-426d-9a75-e25bee6e158f · outbound

This paper cites Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.843903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0babf88d-6996-4337-a4be-c1678e7de9e2 · outbound

This paper cites LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:48.948801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a0d854-3cc7-498b-a52b-adeb1053b518 · outbound

This paper cites FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.048605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13cd30eb-32eb-4858-8572-648f43d32802 · outbound

This paper cites SlimGPT: Layer-wise Structured Pruning for Large Language Models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs SlimGPT: Layer-wise Structured Pruning for Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.156211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cc4047b-c45d-41e2-bd74-8d6fb8e41660 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720, 2023.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720, 2023

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.250473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f61d447f-138e-41a6-8ae8-70bbd193dbde · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.507829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16afe5be-f828-4d8e-98fe-8c1cfbc0676c · outbound

This paper cites Compact language models via pruning and knowledge distillation.Advances in Neural Information Processing Systems, 37:41076–41102, 2024.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Compact language models via pruning and knowledge distillation.Advances in Neural Information Processing Systems, 37:41076–41102, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.586477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09872026-eec2-4148-a4af-b191cb9db28a · outbound

This paper cites Fusegpt: Learnable layers fusion of generative pre-trained transformers.arXiv preprint arXiv:2411.14507, 2024.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Fusegpt: Learnable layers fusion of generative pre-trained transformers.arXiv preprint arXiv:2411.14507, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.661378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e305a96-960d-4161-8d27-4aa42b1435f8 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs A Simple and Effective Pruning Approach for Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.733071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997c0ad8-4bba-4af0-97d2-34bddd8dd6cf · outbound

This paper cites Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.796812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af5bdcb-e5ad-485c-a00b-53792290b617 · outbound

This paper cites Qwen3 Technical Report.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Qwen3 Technical Report

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.879388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc5502e-2347-4934-90b6-4f3d81b1d427 · outbound

This paper cites LaCo: Large Language Model Pruning via Layer Collapse.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs LaCo: Large Language Model Pruning via Layer Collapse

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:49.976362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01e62b67-372f-45cc-9958-c6941e61aae1 · outbound

This paper cites Pangu ultra: Pushing the limits of dense large language models on ascend npus.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Pangu ultra: Pushing the limits of dense large language models on ascend npus

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:50.065340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 504e655c-17b9-47f1-a380-4b33fe3af8a6 · outbound

This paper cites Root mean square layer normalization.Advances in Neural Information Processing Systems, 32, 2019.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Root mean square layer normalization.Advances in Neural Information Processing Systems, 32, 2019

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:03:50.635206Z

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 387bde6f-6707-497d-bb2a-e26386318834 · outbound

This paper cites LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:50.150580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5187db35-4762-4cc3-b373-f26c1d62d21e · outbound

This paper cites Transformers without Normalization.

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs Transformers without Normalization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:50.230653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.