Paper Citation Record · LEDGER

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource

As of 4 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 4 inbound Pith citation observations for arXiv:2506.12119.

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

pith.paper-citation-record.v1
2506.12119 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T00:05:08.916339Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T17:14:53.648013Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T21:16:14.401711Z

Reference resolution

58 of 58 outbound references displayed

verified exact43
verified fuzzy6
unresolved1
parse uncertain0
malformed identifier4
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 67bd1f81-0502-42bc-852f-28eb8af6e605 · outbound

This paper cites Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.697749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 720e2220-8bbb-4aa2-a9d2-c3bb106282cd · outbound

This paper cites GPT-4 Technical Report.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource GPT-4 Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.756643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4debeef8-78e4-41ac-836e-fbd329edadc5 · outbound

This paper cites Qwen Technical Report.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Qwen Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.717451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0c7743e0-2f3e-4b5c-b91f-d3ec0214afeb · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.668876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 50a7e440-700a-4451-ad34-8fd06b023afa · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Evaluating Large Language Models Trained on Code

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.653230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 63be7365-d7be-406f-9b8f-6a05d2692a2d · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.628122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3776b774-c4dd-4521-8e09-b36e6091591b · outbound

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

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.649244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7fd1a61c-c263-4df7-877d-a7407350d110 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.619877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 99b7a461-7143-4ffa-9188-214ec6836b99 · outbound

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

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.645109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 671114e8-7e57-4473-9d43-644129e0cc27 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.623838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 80715de0-fd37-4ba8-9111-0e32dab9e258 · outbound

This paper cites Are We Done with MMLU?.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Are We Done with MMLU?

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.753599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ca0b421a-e734-4678-a90d-d4c2e5a5216b · outbound

This paper cites Upcycling Large Language Models into Mixture of Experts.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Upcycling Large Language Models into Mixture of Experts

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.640835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6145d918-0fbc-413b-b2c1-d7e71676f5db · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Measuring Massive Multitask Language Understanding

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.733573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d61ca962-7b3d-4d55-bccc-4f8b42063e92 · outbound

This paper cites Measuring Coding Challenge Competence With APPS.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Measuring Coding Challenge Competence With APPS

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.741307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 76bb2438-b698-4c4e-9fc4-cd96dabde688 · outbound

This paper cites Scaling Laws and Interpretability of Learning from Repeated Data.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Scaling Laws and Interpretability of Learning from Repeated Data

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T00:05:47.681018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation be1ee3fa-942f-46f9-91ea-080e43d7e39e · outbound

This paper cites Case-based or rule-based: How do transformers do the math? In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Case-based or rule-based: How do transformers do the math? In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T00:05:47.908061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 45b3ea26-9255-47c5-95f8-481f39e6f447 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T00:05:47.772946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7e2ae28e-cb49-4ff8-be1c-6643b83d5d7d · outbound

This paper cites Mixtral of Experts.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Mixtral of Experts

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.677472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation add9a803-4985-4aa2-9871-2832581282d2 · outbound

This paper cites Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.760189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 61bc8a6f-2712-46f8-98c8-3bd72cc4d071 · outbound

This paper cites RACE: Large-scale ReAding comprehension dataset from examinations.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource RACE: Large-scale ReAding comprehension dataset from examinations

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T00:05:47.928836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0e970b19-7d99-4dbf-8651-83bec4b3f8ff · outbound

This paper cites doi: 10.18653/v1/D17-1082.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource doi: 10.18653/v1/D17-1082

Reference 21

Resolution: verified exact; doi, observed 2026-05-22T00:05:47.437184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e9326b72-715d-4dc0-9d74-320525926010 · outbound

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

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.599569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a6bd0cf1-c1d0-4723-b22d-883c265bd2df · outbound

This paper cites CMMLU: Measuring massive multitask language understanding in Chinese.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource CMMLU: Measuring massive multitask language understanding in Chinese

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.713817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5d54bad5-dbfe-43d1-a3f7-0e20e17efeee · outbound

This paper cites Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.673917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e6474934-de1e-434c-a960-ef13542efa22 · outbound

This paper cites A Closer Look into Mixture-of-Experts in Large Language Models.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource A Closer Look into Mixture-of-Experts in Large Language Models

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.615634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a4a27b31-7bb1-443b-97ea-83b53fd4c023 · outbound

This paper cites Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.763501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cc3bb2fe-81f6-4359-b1a0-b63f930cd457 · outbound

This paper cites s1: Simple test-time scaling.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource s1: Simple test-time scaling

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.766515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation de338e06-1efe-4901-a4f1-aa87dc3d8dcd · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.701773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cf1ce965-94ca-4586-aec1-c7217c3ce010 · outbound

This paper cites Qwen2.5 Technical Report.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Qwen2.5 Technical Report

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.603099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f142a64e-c741-441d-9f0f-2b83526640db · outbound

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

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.665184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3d5cff0a-837d-4269-af6d-91a197dd9186 · outbound

This paper cites SocialIQA: Commonsense Reasoning about Social Interactions.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource SocialIQA: Commonsense Reasoning about Social Interactions

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.632020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation deca0ad1-5b52-43ef-80ba-00664d4e4099 · outbound

This paper cites GLU Variants Improve Transformer.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource GLU Variants Improve Transformer

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.689044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a24f0248-17f3-449a-9788-d79be0193865 · outbound

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

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.636429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 57adffde-3aaf-40a4-9487-9f4b88680d13 · outbound

This paper cites MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T00:05:47.661338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6352e637-873e-4838-8951-231343952c26 · outbound

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

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.725732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 27906ec8-7f4f-436f-851a-d54a2ef1a3e9 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource LLaMA: Open and Efficient Foundation Language Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.596018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f0840b4a-20cd-425a-bafe-30c7d1e93f58 · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.611002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation acd6bcd6-c948-4822-83f3-84d3863ec5e6 · outbound

This paper cites Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.709852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f4813c2c-ab4e-474b-81cb-1325c1519b49 · outbound

This paper cites Crowdsourcing Multiple Choice Science Questions.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Crowdsourcing Multiple Choice Science Questions

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.737525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1b2f0dfb-fcf9-417d-af44-3f0c70d3fa30 · outbound

This paper cites LiveBench: A Challenging, Contamination-Limited LLM Benchmark.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.657250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6f62da38-a2af-4123-b8eb-4d460fe861f3 · outbound

This paper cites Yuan 2.0-M32: Mixture of Experts with Attention Router.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Yuan 2.0-M32: Mixture of Experts with Attention Router

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.684980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 75dbee06-450c-400e-901d-4372730c132f · outbound

This paper cites CLUE: A Chinese Language Understanding Evaluation Benchmark.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource CLUE: A Chinese Language Understanding Evaluation Benchmark

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.693217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec96d003-d047-40b7-9b72-a953203bad57 · outbound

This paper cites To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.745161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 82656867-18ed-4b56-a48e-7d77622b7fc6 · outbound

This paper cites Qwen2 Technical Report.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Qwen2 Technical Report

Reference 44

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T00:05:47.769523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3f5a99a0-ade0-42fc-a449-04d9131a51f9 · outbound

This paper cites Evaluating the Performance of Large Language Models on GAOKAO Benchmark.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Evaluating the Performance of Large Language Models on GAOKAO Benchmark

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.729661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c9a4be39-084a-460a-924a-2c2956d9beb0 · outbound

This paper cites Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.705926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 280b87f7-95ae-40a7-a53d-0a4de84dd515 · outbound

This paper cites MoEfication: Transformer Feed-forward Layers are Mixtures of Experts.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource MoEfication: Transformer Feed-forward Layers are Mixtures of Experts

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-22T00:05:47.722120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 73a841bc-ceb5-48fe-aa7d-35c89d7577a5 · outbound

This paper cites AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.607647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 37db8820-005c-4f5c-810f-4550f796cf64 · outbound

This paper cites ST-MoE: Designing Stable and Transferable Sparse Expert Models.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource ST-MoE: Designing Stable and Transferable Sparse Expert Models

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-22T00:05:47.749121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c775ce18-7b75-4ff4-a612-c65fadaeda18 · outbound

This paper cites sparsity.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource sparsity

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T00:05:47.934246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 32b79e37-c0b1-4d4d-ba05-1f47794715ca · outbound

This paper cites Our conclusion regarding a consistent optimal activation rate contradicts the findings of Abnar et al.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Our conclusion regarding a consistent optimal activation rate contradicts the findings of Abnar et al

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T00:05:47.931706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2f771291-94bb-47d9-97bb-4d7620ac7e1e · outbound

This paper cites Symbol Definition D Dataset size in tokens.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Symbol Definition D Dataset size in tokens

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T00:05:47.926158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fb94c589-bf13-4033-8955-2cefd68e4ba3 · outbound

This paper cites Hyperparameters shared by all experiments: L = 16, S = 2048, Dm = 1408, Dffn = 3904, H = 11, Dh = 128, ζ =.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Hyperparameters shared by all experiments: L = 16, S = 2048, Dm = 1408, Dffn = 3904, H = 11, Dh = 128, ζ =

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T00:05:47.923133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bd6b37dc-7c8b-4eb4-b134-6ce18c7d0397 · outbound

This paper cites Hyperparameters shared by all experiments: L = 16, S = 2048, Dm = 1408, Dffn = 3904, H = 11, Dh = 128, ζ =.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Hyperparameters shared by all experiments: L = 16, S = 2048, Dm = 1408, Dffn = 3904, H = 11, Dh = 128, ζ =

Reference 54

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T00:05:47.910862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b8782ba1-4c80-4947-86f7-3024bd30da70 · outbound

This paper cites Hyperparameters shared by all experiments: L = 24 , S = 2048 , Dm = 2048 , Dffn = 5464, H = 16, Dh = 128, ζ = 85.3.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Hyperparameters shared by all experiments: L = 24 , S = 2048 , Dm = 2048 , Dffn = 5464, H = 16, Dh = 128, ζ = 85.3

Reference 55

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T00:05:47.919733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1a96db6e-6dff-4194-a7e2-2f09af30d116 · outbound

This paper cites Hyperparameters shared by all experiments: L = 24, S = 2048, Dm = 1408, Dffn = 3904, H = 11, Dh =.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Hyperparameters shared by all experiments: L = 24, S = 2048, Dm = 1408, Dffn = 3904, H = 11, Dh =

Reference 56

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T00:05:47.916591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0c732526-fbd7-4939-a649-1f27cdce5ff5 · outbound

This paper cites Hyperparameters shared by all experiments: L = 24, S = 2048, Dm = 2048, Dffn = 5464, H = 16, Dh =.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Hyperparameters shared by all experiments: L = 24, S = 2048, Dm = 2048, Dffn = 5464, H = 16, Dh =

Reference 57

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T00:05:47.913675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b96edb45-ff34-44d4-8978-591c54afd2c8 · outbound

This paper cites an unresolved cited work.

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-05-22T00:05:47.937242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation da395097-aacb-41c0-9cc2-cb5f70a3391c · inbound

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices cites this paper.

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource

Reference 177

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T00:02:51.345572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 536b5653-6a3a-44dd-a0f1-6851b4eae42e · inbound

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices cites this paper.

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource

Reference 177

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T00:02:51.345572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b71165e9-f491-42be-b78c-983a1bbe4575 · inbound

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices cites this paper.

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource

Reference 177

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T07:59:50.190755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 472c2027-c057-4da0-86e1-c27b0c340337 · inbound

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts cites this paper.

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T21:16:14.403107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.