Paper Citation Record · LEDGER

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks

As of 18 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2505.15414.

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

pith.paper-citation-record.v1
2505.15414 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:24:00.873308Z

measured 46 of 46 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T01:39:29.681621Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T03:24:12.966811Z

Reference resolution

45 of 45 outbound references displayed

verified exact1
verified fuzzy30
unresolved11
parse uncertain1
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 13d87c56-375b-46a8-8a0d-346442c8da75 · outbound

This paper cites Cnn mixture- of-depths.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Cnn mixture- of-depths

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:06.069066Z

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 5955cf6d-ed92-42c0-96af-05ca9fa94802 · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:24:05.984198Z

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 96f4ab52-d866-4f7b-aac4-fa6b936dd4da · outbound

This paper cites Adamv-moe: Adaptive multi-task vision mixture-of- experts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Adamv-moe: Adaptive multi-task vision mixture-of- experts

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:05.917478Z

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 dc4002fa-a2bd-40fc-8f01-c8a8488f97d7 · outbound

This paper cites Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:58.172551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e5d2e1e-385e-4e1e-a60a-c4da269eb563 · outbound

This paper cites Editing factual knowledge in language models.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Editing factual knowledge in language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:05.709176Z

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 ccb394a9-2ec0-444e-9ff6-25bed08d6f25 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Imagenet: A large-scale hierarchical image database

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:58.313312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ace745-8c51-4312-8e1f-c16018d37124 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks An image is worth 16x16 words: Transformers for image recognition at scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:58.365441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce600041-3fcf-4e20-ae9b-c6a3bd9c6c31 · outbound

This paper cites Learning factored representations in a deep mixture of ex- perts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Learning factored representations in a deep mixture of ex- perts

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:05.255190Z

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 631009a8-1678-45f5-8cd9-fc1e32b6ee23 · outbound

This paper cites Switch transformers: scaling to trillion parameter models with sim- ple and efficient sparsity.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Switch transformers: scaling to trillion parameter models with sim- ple and efficient sparsity

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:05.017008Z

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 904a807d-9fad-443c-b007-efd9c1b9af11 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Transformer feed-forward layers are key-value memories

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.772928Z

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 8917cfb3-4389-420f-8abf-d3aeb1e354d5 · outbound

This paper cites Paca-vit: Learning patch-to- cluster attention in vision transformers.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Paca-vit: Learning patch-to- cluster attention in vision transformers

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.669288Z

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 8964dc15-d008-444b-895d-4638759fe8cd · outbound

This paper cites Jacobs, Michael I.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Jacobs, Michael I

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.563268Z

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 c0cca5f0-338b-4d66-b4ab-4b96b2d64bf8 · outbound

This paper cites Learning multiple layers of features from tiny images.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Learning multiple layers of features from tiny images

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.461482Z

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 fdbd8935-4465-4e1a-b3e0-07f5e5f785d2 · outbound

This paper cites Gshard: Scaling giant models with conditional computation and automatic sharding.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Gshard: Scaling giant models with conditional computation and automatic sharding

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.355795Z

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 8d1fdac2-013a-4550-a0f4-5c03088be907 · outbound

This paper cites M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:24:01.043720Z

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 1257fd36-0f29-431a-919b-32b6b706072a · outbound

This paper cites Liang, Yiming Cui, Qifan Wang, Tong Geng, Wen- guan Wang, and Dongfang Liu.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Liang, Yiming Cui, Qifan Wang, Tong Geng, Wen- guan Wang, and Dongfang Liu

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.249861Z

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 12356daa-86e5-4abf-85e6-88b94ce3a4e5 · outbound

This paper cites Expediting large-scale vision transformer for dense predic- tion without fine-tuning.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Expediting large-scale vision transformer for dense predic- tion without fine-tuning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.163106Z

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 378c6db7-499f-468c-8b75-a6a4797b9128 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Swin transformer: Hierarchical vision transformer using shifted windows

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:04.060206Z

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 cfeab651-0f64-484d-bf52-138c75035197 · outbound

This paper cites A ConvNet for the 2020s.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks A ConvNet for the 2020s

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:03.916903Z

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 14c2299d-7fc3-4264-83b6-6e543c39779d · outbound

This paper cites SGDR: stochastic gradient descent with warm restarts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks SGDR: stochastic gradient descent with warm restarts

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:03.672553Z

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 0b6889e2-02a3-4894-84e1-f53876c982d0 · outbound

This paper cites Decoupled weight decay regularization.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Decoupled weight decay regularization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:59.331213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c3a8ffd-db7a-465b-8cb4-05de588b739d · outbound

This paper cites Data-free dynamic compression of cnns for tractable effi- ciency.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Data-free dynamic compression of cnns for tractable effi- ciency

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:03.542747Z

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 910002f6-248c-44df-840b-cc112a17533a · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:24:03.433425Z

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 1924e943-e112-456a-9d42-9089d2f203b2 · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:03.318844Z

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 93298046-c3cc-4af2-a7fa-5028a97c44bf · outbound

This paper cites Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:59.618392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4740d5-ad37-43e8-81a3-099d565a82e3 · outbound

This paper cites Scaling vision with sparse mix- ture of experts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Scaling vision with sparse mix- ture of experts

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:03.233111Z

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 29066870-2cf7-45e2-9ee2-4dfeaee96589 · outbound

This paper cites Le, Geoffrey E.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Le, Geoffrey E

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:03.091241Z

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 93ca7a46-5006-45ea-b77f-850162a1cd72 · outbound

This paper cites Training data-efficient image transformers & distillation through at- tention.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Training data-efficient image transformers & distillation through at- tention

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:02.997813Z

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 4a86029b-a046-41b3-a71a-2c06788b8ef4 · outbound

This paper cites Gomez, Łukasz Kaiser, and Il- lia Polosukhin.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Gomez, Łukasz Kaiser, and Il- lia Polosukhin

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:59.844233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a5c7d5-5681-4b63-93e7-4cefdb72b6e5 · outbound

This paper cites Evo-vit: Slow-fast token evolution for dynamic vision transformer.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Evo-vit: Slow-fast token evolution for dynamic vision transformer

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:02.847038Z

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 464e8b07-e0fd-432c-8be5-2bf496bf8ce9 · outbound

This paper cites Width & depth pruning for vision transform- ers.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Width & depth pruning for vision transform- ers

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:02.716047Z

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 46ccf3f7-4c0f-40f7-a545-e83710bc045c · outbound

This paper cites MoEfication: Transformer feed-forward layers are mixtures of experts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks MoEfication: Transformer feed-forward layers are mixtures of experts

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:02.606178Z

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 3f4d5c2c-c54e-47ca-b10d-a5de3b9728c6 · outbound

This paper cites Emergent modularity in pre- trained transformers.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Emergent modularity in pre- trained transformers

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:02.476896Z

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 4ecc2086-d3ea-4b26-92e3-d796a7e1ac49 · outbound

This paper cites Vision transformer pruning, 2021.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Vision transformer pruning, 2021

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:02.348371Z

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 3e76fd50-b792-4bb0-8f2a-d146be86147a · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:24:02.223252Z

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 4d79b088-41e4-4879-86f9-9e8cf99b9a26 · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:24:02.107505Z

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 a314ddf4-c944-4124-9f95-dd19b142c509 · outbound

This paper cites [32] rely on weight co-activation graphs and a manually set number of experts.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks [32] rely on weight co-activation graphs and a manually set number of experts

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:01.989832Z

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 522bc121-5af9-47d9-a820-fbe113f01fe4 · outbound

This paper cites Our results on ImageNet-1k validate this design, showing performance gains in vision tasks.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Our results on ImageNet-1k validate this design, showing performance gains in vision tasks

Reference 40

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T15:24:01.880385Z

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 3b136eb2-b614-4b1f-ae4b-9a2d4acda1d6 · outbound

This paper cites Despite structural differences, all variants benefit from fewer MACs, reduced parameter counts and competitive final accuracies.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Despite structural differences, all variants benefit from fewer MACs, reduced parameter counts and competitive final accuracies

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:01.716240Z

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 894ff46d-85d3-4a68-a614-7325debf04fa · outbound

This paper cites We compare our default method, HDBSCAN, against other density-based methods (DBSCAN, OPTICS) as well as partition-based alternatives (K-Means, BIRCH).

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks We compare our default method, HDBSCAN, against other density-based methods (DBSCAN, OPTICS) as well as partition-based alternatives (K-Means, BIRCH)

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:01.595145Z

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 cb20b120-ee0d-45e7-810e-47765ebcac3e · outbound

This paper cites For the ex- traction strategy, we consider two methods for selecting the hidden neurons of each expert.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks For the ex- traction strategy, we consider two methods for selecting the hidden neurons of each expert

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:01.479245Z

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 d9f42eb1-d16b-48a4-be7b-9e98b49b916f · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 44

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T15:24:01.344918Z

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 f8db9359-6281-4632-8542-2f31436fb03a · outbound

This paper cites Notably, the earlier lay- ers do not exhibit any formed clusters, reflecting the more general feature representations in shallower layers.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Notably, the earlier lay- ers do not exhibit any formed clusters, reflecting the more general feature representations in shallower layers

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:24:01.184009Z

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 28c7a30f-8255-4b0c-b108-e1bfc14aed30 · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 2017

Resolution: parse uncertain; no resolver link, observed 2026-08-07T15:23:59.912198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e0dfc0a-34fe-44b9-a81d-761399d9620c · outbound

This paper cites an unresolved cited work.

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks Unresolved cited work

Reference 2021

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:24:05.475124Z

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.

Pith citing papers

Observation d2073092-f490-4894-ba08-6d98b6206114 · inbound

CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection cites this paper.

CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:24:12.968335Z

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.