Paper Citation Record · LEDGER

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models

As of 14 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2608.07890.

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

pith.paper-citation-record.v1
2608.07890 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:49:01.983631Z

measured 33 of 33 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 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

33 of 33 outbound references displayed

verified exact3
verified fuzzy10
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 891266e0-263e-4b0a-812c-2e19b7558e02 · outbound

This paper cites DiEP: Adaptive mixture-of-experts compression through differentiable expert pruning.arXiv preprint arXiv:2509.16105, 2025.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models DiEP: Adaptive mixture-of-experts compression through differentiable expert pruning.arXiv preprint arXiv:2509.16105, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.879932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4da1fb-5c05-4358-9927-35aed7e48002 · outbound

This paper cites Task-Specific Expert Pruning for Sparse Mixture-of-Experts.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Task-Specific Expert Pruning for Sparse Mixture-of-Experts

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.883488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b39d4a-1d0a-409e-8ab1-43192e79e837 · outbound

This paper cites A provably effective method for pruning experts in fine-tuned sparse mixture-of-experts.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models A provably effective method for pruning experts in fine-tuned sparse mixture-of-experts

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.591859Z

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 fde8606f-f69b-4ae0-a773-5cc57c8d90a9 · outbound

This paper cites BoolQ: Exploring the surprising difficulty of natural yes/no questions.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models BoolQ: Exploring the surprising difficulty of natural yes/no questions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.581959Z

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 afac1b59-746f-4cd5-abfb-41c7e752b8b5 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.893687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3ca1928-df1c-4ea2-abf1-5a6354dd8255 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.897288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 084f6780-ac34-4150-865a-b0b9955df576 · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.900748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157e458a-320c-46ce-976c-6967b58d8805 · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models QLoRA: Efficient Finetuning of Quantized LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.904132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 036ee345-af6c-415f-8f2b-39506d163821 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.572169Z

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 a4f1cfb4-d4c0-4ede-8a9e-9160c8263fe2 · outbound

This paper cites LightEval: A lightweight framework for LLM evaluation.https://github.com/huggingface/lighteval, 2023.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models LightEval: A lightweight framework for LLM evaluation.https://github.com/huggingface/lighteval, 2023

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.562429Z

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 6eb2fba6-29fb-4a7f-88c4-ed08907ba91b · outbound

This paper cites Parameter-efficient transfer learning for NLP.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Parameter-efficient transfer learning for NLP

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.552596Z

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 918bfb6e-f589-4bae-98a8-343eaf2f895f · outbound

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

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.917699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb1789aa-30a0-4585-8c56-62f9d3a1e00e · outbound

This paper cites Whatgetsactivated: Uncovering domain and driver experts in MoE language models.arXiv preprint arXiv:2601.10159, 2026.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Whatgetsactivated: Uncovering domain and driver experts in MoE language models.arXiv preprint arXiv:2601.10159, 2026

Reference 13

Resolution: verified exact; raw_fallback, observed 2026-08-12T00:49:02.370354Z

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 ada29a1d-99c0-4f84-9947-0cfbe04b5298 · outbound

This paper cites Isretraining-freeenough? thenecessityofroutercalibrationforefficient MoE compression.arXiv preprint arXiv:2603.02217, 2026.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Isretraining-freeenough? thenecessityofroutercalibrationforefficient MoE compression.arXiv preprint arXiv:2603.02217, 2026

Reference 14

Resolution: verified exact; raw_fallback, observed 2026-08-12T00:49:02.303879Z

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 61fbfbd6-6321-458f-afce-2f8738c702b4 · outbound

This paper cites Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.926938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 668edeb3-9b5b-46f8-9d2e-8c89499caea9 · outbound

This paper cites Mixtral of Experts.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Mixtral of Experts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.930118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70273fa2-e53b-49f0-b876-25863bed257d · outbound

This paper cites Memory-efficient NLLB-200: Language-specificexpertpruningofamassivelymultilingualmachinetranslationmodel.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Memory-efficient NLLB-200: Language-specificexpertpruningofamassivelymultilingualmachinetranslationmodel

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.542119Z

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 c0aaf6a8-0f4e-4399-a981-702dd0f0062f · outbound

This paper cites REAP the Experts: Why Pruning Prevails for One-Shot MoE compression.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.936166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bbb5269-70e9-497e-a708-2d9b61e8cda6 · outbound

This paper cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.939879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9863d2d-eca5-4e8a-ab06-bd41c10e4a7e · outbound

This paper cites Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.943207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf37a876-1492-4c08-936b-a8f028faad5f · outbound

This paper cites Prefix-tuning: Optimizing continuous prompts for generation.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Prefix-tuning: Optimizing continuous prompts for generation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.531509Z

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 a541499f-7628-4625-b67e-c2c8ef29dd68 · outbound

This paper cites Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.949181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91488c25-d831-41dd-938f-b4306befc0b7 · outbound

This paper cites Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.952312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1501c59d-cf2d-4ce1-9022-527a23fa0ca4 · outbound

This paper cites Not all experts are equal: Efficient expert pruning and skipping for mixture-of-experts large language models.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Not all experts are equal: Efficient expert pruning and skipping for mixture-of-experts large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.521484Z

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 3ef82a77-8cde-4d14-b1a4-1ebfe6ae5d10 · outbound

This paper cites an unresolved cited work.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:49:02.511001Z

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 9e90403c-22a1-48db-9172-f5027fa6feb6 · outbound

This paper cites SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.961675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97a3bce9-c087-4993-9250-a946bc1fff60 · outbound

This paper cites Qwen1.5-MoE: Matching 7B model performance with 1/3 activated parameters.https: //qwenlm.github.io/blog/qwen-moe/, 2024.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Qwen1.5-MoE: Matching 7B model performance with 1/3 activated parameters.https: //qwenlm.github.io/blog/qwen-moe/, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.500646Z

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 7e846139-9d62-4abc-bce9-962c39b09373 · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.967993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b984f894-7398-4769-a8da-7eb04e365d00 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.971209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c1ff876-aaa7-4670-b552-d97ffb4eab24 · outbound

This paper cites LoRA without regret.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models LoRA without regret

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:49:02.488748Z

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 717cab9f-b213-46b4-b318-1b12bb4fa1b3 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.977418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1e88265-d0c6-4b5e-8580-a9fd5f552264 · outbound

This paper cites MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T00:49:01.980607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24536dcf-c66d-4c6a-baf5-5c06b7590a19 · outbound

This paper cites MoE pathfinder: Trajectory-driven expert pruning.arXiv preprint arXiv:2512.18425, 2025.

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models MoE pathfinder: Trajectory-driven expert pruning.arXiv preprint arXiv:2512.18425, 2025

Reference 33

Resolution: verified exact; raw_fallback, observed 2026-08-12T00:49:02.113892Z

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

No inbound Pith citation observations are available.