Paper Citation Record · LEDGER

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models

As of 8 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2505.20225.

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

pith.paper-citation-record.v1
2505.20225 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:02:51.437970Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

40 of 40 outbound references displayed

verified exact1
verified fuzzy29
unresolved9
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8f7cb68c-c85a-429a-b05b-0f20b46cd02f · outbound

This paper cites Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:44.098280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9399a12-234f-4d58-953b-785a7351a57b · outbound

This paper cites Emergent and predictable memorization in large language models.Advances in Neural Information Processing Systems, 36:28072–28090, 2023.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Emergent and predictable memorization in large language models.Advances in Neural Information Processing Systems, 36:28072–28090, 2023

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:44.185028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1066643-3fa7-4900-bf49-dd1df442b687 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Pythia: A suite for analyzing large language models across training and scaling

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:57.347994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 19b5c372-8288-4763-b652-6a08202985e1 · outbound

This paper cites PIQA: Reasoning about physical commonsense in natural language.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models PIQA: Reasoning about physical commonsense in natural language

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:57.131655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4cc5e103-b3f9-402d-a872-6b5f11822cc6 · outbound

This paper cites On the representation collapse of sparse mixture of experts.Proc.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models On the representation collapse of sparse mixture of experts.Proc

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:56.991684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 17867122-d6c0-4dd7-a013-08ec8d2efbcf · outbound

This paper cites Think you have solved question answering? Try ARC, the ai2 reasoning challenge.ArXiv preprint, 2018.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Think you have solved question answering? Try ARC, the ai2 reasoning challenge.ArXiv preprint, 2018

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:56.694982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 979caedc-952a-44ab-8c32-168840215b12 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.JMLR, 2022.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.JMLR, 2022

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:44.870448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce109ed3-19b0-4f5f-8f44-e4aa15571a9f · outbound

This paper cites A framework for few-shot language model evaluation, 2023.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models A framework for few-shot language model evaluation, 2023

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:46.280209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0260bff8-ab34-40aa-a0e4-839c568c536f · outbound

This paper cites Fastmoe: A fast mixture-of-expert training system.ArXiv preprint, 2021.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Fastmoe: A fast mixture-of-expert training system.ArXiv preprint, 2021

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:56.459809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 837e542e-4add-4452-860f-13db535962b7 · outbound

This paper cites Measuring massive multitask language understanding.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Measuring massive multitask language understanding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:56.294055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2a02d5d3-a089-44f8-a061-99e75156a5d4 · outbound

This paper cites Rae, and Laurent Sifre.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Rae, and Laurent Sifre

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:56.108386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1ec5f9de-fb94-47fb-8161-ede4a9723c2c · outbound

This paper cites MiniCPM: Unveiling the potential of small language models with scalable training strategies.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models MiniCPM: Unveiling the potential of small language models with scalable training strategies.ArXiv preprint, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:55.955220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4d514ff9-0f8f-4d37-909c-3756780d7cc0 · outbound

This paper cites Demystifying Verbatim Memorization in Large Language Models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Demystifying Verbatim Memorization in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:48.631328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf0d8ca-ff43-48f7-8858-1af889e32b07 · outbound

This paper cites Tutel: Adaptive mixture-of-experts at scale.Proc.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Tutel: Adaptive mixture-of-experts at scale.Proc

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:55.778999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7836f992-70e3-44e5-96aa-b364a4855eee · outbound

This paper cites Mixtral of experts.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Mixtral of experts.ArXiv preprint, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:55.645820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 600cf498-58d5-4668-a673-ceed6b75624c · outbound

This paper cites Kingma and Jimmy Ba.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Kingma and Jimmy Ba

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:48.903883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91fb215e-94c9-4a4a-ba68-68fac46da7b2 · outbound

This paper cites Gshard: Scaling giant models with condi- tional computation and automatic sharding.ArXiv preprint, 2020.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Gshard: Scaling giant models with condi- tional computation and automatic sharding.ArXiv preprint, 2020

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:55.494798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 57be5bee-4181-4a08-a047-9b862dc2c2d6 · outbound

This paper cites Base layers: Simplifying training of large, sparse models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Base layers: Simplifying training of large, sparse models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:55.322288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 32991eed-24c1-4f1d-8a80-38227fbea49e · outbound

This paper cites DataComp-LM: In search of the next generation of training sets for language models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models DataComp-LM: In search of the next generation of training sets for language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:55.097841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 205aaada-f018-4f97-8661-88b85581ae3c · outbound

This paper cites DeepSeek-V2: A strong, economical, and efficient mixture-of-experts language model.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models DeepSeek-V2: A strong, economical, and efficient mixture-of-experts language model.ArXiv preprint, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:54.915523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2488fdc3-327d-4a77-a490-b7155880a952 · outbound

This paper cites Deepseek-v3 technical report.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Deepseek-v3 technical report.ArXiv preprint, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:54.699463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c893d78f-3ea9-4cd1-bfd2-30062ab246b4 · outbound

This paper cites Tending Towards Stability: Convergence Challenges in Small Language Models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Tending Towards Stability: Convergence Challenges in Small Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:02:51.956017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 347390f4-ba5f-4991-9f2d-07015a526b31 · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation, 2025.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models The llama 4 herd: The beginning of a new era of natively multimodal ai innovation, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:49.622260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377c94ac-495e-4e96-84f2-1f3ca751b85a · outbound

This paper cites Can a suit of armor conduct electricity? A new dataset for open book question answering.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Can a suit of armor conduct electricity? A new dataset for open book question answering

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:54.543552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2e3005a9-6025-4c94-977a-647799d1facc · outbound

This paper cites OLMoE: Open mixture-of- experts language models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models OLMoE: Open mixture-of- experts language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:54.352140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 42cb3bec-3ff6-43e2-9c9d-19449809682d · outbound

This paper cites Attributing mode collapse in the fine-tuning of large language models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Attributing mode collapse in the fine-tuning of large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:54.222040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 59ccef2d-e88b-4f1f-b0ff-247c8dcb8098 · outbound

This paper cites Deepspeed-moe: Advancing mixture-of- experts inference and training to power next-generation ai scale.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Deepspeed-moe: Advancing mixture-of- experts inference and training to power next-generation ai scale

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:54.005119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9049d2e6-f188-4158-a940-595c4b82c435 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Winogrande: An adversarial winograd schema challenge at scale

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:53.845348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ee80a897-dbc9-4f7e-8163-6394dfc5ff60 · outbound

This paper cites Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.ArXiv preprint, 2017.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.ArXiv preprint, 2017

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:53.671642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 604aefab-5833-440f-b97d-1813b83ca0a6 · outbound

This paper cites JetMoE: Reaching llama2 performance with 0.1 m dollars.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models JetMoE: Reaching llama2 performance with 0.1 m dollars.ArXiv preprint, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:53.496149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1fc7123e-646d-4393-8b86-6fab5e0cb37f · outbound

This paper cites Megatron-lm: Training multi-billion parameter language models using model parallelism.ArXiv preprint, 2019.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Megatron-lm: Training multi-billion parameter language models using model parallelism.ArXiv preprint, 2019

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:53.348965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3b62554e-adc6-4893-8488-a990ba9a1b9b · outbound

This paper cites Layer by Layer: Uncovering Hidden Representations in Language Models.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Layer by Layer: Uncovering Hidden Representations in Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:50.561305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59facc6e-3fac-4b6c-90c8-1093272969e9 · outbound

This paper cites Free dolly: Introducing the world’s first truly open instruction-tuned llm.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Free dolly: Introducing the world’s first truly open instruction-tuned llm

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:53.158449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b53b6c84-44e8-4434-9e21-a2ac9b6741f3 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.ArXiv preprint, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:52.961360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 675da49c-9505-4b43-86d1-2942a9db9fec · outbound

This paper cites LLM Circuit Analyses Are Consistent Across Training and Scale.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models LLM Circuit Analyses Are Consistent Across Training and Scale

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:50.878275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7797fdd4-71a3-47c6-ab3e-5ba497646968 · outbound

This paper cites OpenMoE: An early effort on open mixture-of-experts language models.ArXiv preprint, 2024.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models OpenMoE: An early effort on open mixture-of-experts language models.ArXiv preprint, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:52.797912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 236e214e-2813-4c4f-a6d9-7e262475f5f7 · outbound

This paper cites M6-T: Exploring sparse expert models and beyond.arXiv preprint, 2021.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models M6-T: Exploring sparse expert models and beyond.arXiv preprint, 2021

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:52.594448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8fb563fd-cd57-47fa-8787-b1992250163a · outbound

This paper cites HellaSwag: Can a machine really finish your sentence? InProc.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models HellaSwag: Can a machine really finish your sentence? InProc

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:52.401440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7475c41a-9ede-430d-bf65-5afe0a0e104e · outbound

This paper cites OPT: Open pre-trained transformer language models.ArXiv preprint, 2022.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models OPT: Open pre-trained transformer language models.ArXiv preprint, 2022

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:02:52.220119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 846f8683-413e-4ca0-842b-a049c33d399f · outbound

This paper cites ST-MoE: Designing stable and transferable sparse expert models.ArXiv preprint, 2022.

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models ST-MoE: Designing stable and transferable sparse expert models.ArXiv preprint, 2022

Reference 40

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:02:51.728312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.