Paper Citation Record · LEDGER

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference

As of 8 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2607.24434.

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

pith.paper-citation-record.v1
2607.24434 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T15:02:37.625143Z

measured 31 of 31 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

31 of 31 outbound references displayed

verified exact0
verified fuzzy0
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 64e02062-c017-4278-a803-7774256413d2 · outbound

This paper cites 2023 , eprint=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2023 , eprint=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.484533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af82585-14cc-4b83-8cc1-5a886b090844 · outbound

This paper cites 2023 , eprint=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2023 , eprint=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.488153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ef27a9f-53db-42ea-9015-c0ecc8b7d72b · outbound

This paper cites International Conference on Learning Representations , year=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference International Conference on Learning Representations , year=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.492875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55bb3ab5-1842-4fc7-91b1-bc98c3adb3f7 · outbound

This paper cites Journal of Machine Learning Research , volume=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Journal of Machine Learning Research , volume=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.496151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4713f8ed-ba82-4d11-9165-fa1064939df5 · outbound

This paper cites 2602.16052 , archivePrefix=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2602.16052 , archivePrefix=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.499668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9418cc9c-14ae-4f62-8abf-2f048f45237c · outbound

This paper cites 2025 , eprint=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2025 , eprint=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.502804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 495f944d-0d64-44c2-8e02-241e8dddc110 · outbound

This paper cites Self-Speculative Decoding for On-device.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Self-Speculative Decoding for On-device

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.505734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49d73e67-0429-40a3-8a4e-9807b34d1f08 · outbound

This paper cites SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.509164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6607f2c-a043-46f2-b4de-129e246b4b71 · outbound

This paper cites 2505.19645 , archivePrefix=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2505.19645 , archivePrefix=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.512797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d43b341f-619b-4357-9565-ffdfce6a3f37 · outbound

This paper cites 2025 , eprint=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2025 , eprint=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.515708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b69a6c9-ad89-49e3-aea5-450f226771a6 · outbound

This paper cites 2510.10302 , archivePrefix=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2510.10302 , archivePrefix=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.518889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6194f41-cda9-4710-b57a-26f9a69f47a4 · outbound

This paper cites 2511.14102 , archivePrefix=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2511.14102 , archivePrefix=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.521920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e207c930-7770-42e3-8c81-40082e424f79 · outbound

This paper cites 2603.09983 , archivePrefix=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2603.09983 , archivePrefix=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.525169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68fa8e58-4876-40ce-9b54-5dfa87a0838b · outbound

This paper cites Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.528129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c156d3c7-517f-42d6-8728-dca1395035dc · outbound

This paper cites an unresolved cited work.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.532084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11e73928-fa4b-49cc-a81c-08ffc7842855 · outbound

This paper cites Semantic Parallelism: Redefining Efficient.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Semantic Parallelism: Redefining Efficient

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.535805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 960c2825-75ae-4754-bbf1-c57e11b65784 · outbound

This paper cites an unresolved cited work.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.538944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e603a26-070c-462a-892b-4522a2cb8d01 · outbound

This paper cites an unresolved cited work.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.541731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc16800e-1ccb-4fde-a0b1-f57cd4e4a4ba · outbound

This paper cites 2024 , eprint=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference 2024 , eprint=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.544751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9193836f-2bf7-4d6d-8319-8913b5d405e9 · outbound

This paper cites an unresolved cited work.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.547776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06ab9746-9193-4bb6-8cf0-570b03a62a8a · outbound

This paper cites Muon is Scalable for LLM Training.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Muon is Scalable for LLM Training

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.550752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44fb7af-a7e3-41d4-8610-8c1ffe425808 · outbound

This paper cites an unresolved cited work.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.554220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e896fde-2a38-41d0-bd5c-095c8fc72161 · outbound

This paper cites Lee and Deming Chen and Tri Dao , booktitle=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Lee and Deming Chen and Tri Dao , booktitle=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.557210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 996de623-8121-40b9-bb3c-fafec6129085 · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.560701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0fb9917-41d5-480a-a52c-66cb2ddf4153 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics , pages=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics , pages=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.563989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2084cf-3293-45a7-97ca-fc92a5e07c23 · outbound

This paper cites Aly and Beidi Chen and Carole-Jean Wu , booktitle=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Aly and Beidi Chen and Carole-Jean Wu , booktitle=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.566907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ad2203-067a-49c0-a69e-efe1f2f3fcfc · outbound

This paper cites MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.574777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2b4e76c-62a7-4897-8fb0-bee4e0ae9eed · outbound

This paper cites EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.590572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 820962ca-f13a-4935-82dd-fd0c15f860c5 · outbound

This paper cites Fiddler:.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference Fiddler:

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.603714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bdd0961-faee-4a84-8de9-560c047f893d · outbound

This paper cites llama.cpp:.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference llama.cpp:

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.614730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9a80390-b09d-411a-80bc-436ca061c25e · outbound

This paper cites NIPS Deep Learning and Representation Learning Workshop , year=.

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference NIPS Deep Learning and Representation Learning Workshop , year=

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T15:02:37.625143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.