Pith. sign in

Paper Citation Record · LEDGER

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models

As of 17 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2505.07680.

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

pith.paper-citation-record.v1
2505.07680 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:15:13.851365Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:56:29.078219Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T20:56:29.568260Z

Reference resolution

55 of 55 outbound references displayed

  • verified exact1
  • verified fuzzy34
  • unresolved20
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d2995a8d-f036-4819-a308-32611d4ef6f6 · outbound

This paper cites Scaling laws for generative mixed-modal language models.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Scaling laws for generative mixed-modal language models

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:15.103664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.553760Z digest=sha256:827013a16f9b56429d077663eae7f794f85e6549586d3bc1bc88655a6360852b

Observation 51e7ce4e-9530-4bdd-8c55-dfab99b32278 · outbound

This paper cites S., Ramjee, R., and Tumanov, A.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models S., Ramjee, R., and Tumanov, A

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:15.080205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.559495Z digest=sha256:92e2de81954bb9254cba96142a2e4277ec429e25a16cdae1c16b6f561d8de702

Observation cd7a78cc-0220-445f-a606-f1bd28d5b8c3 · outbound

This paper cites In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) (2024), pp.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) (2024), pp

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:15.053511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.565871Z digest=sha256:4c4ff1195ec756bf7eca4dedc8fa5a41256000e5657fc9f646f03a409671b1fa

Observation 6e03aba7-2a99-4de8-b68c-905a25151e7b · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.571386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.571386Z digest=sha256:8e01cc6ebb9094504f880469a74abcf6198f1f35d44f8e7d61f8e8c666f5b305

Observation 3bd13680-5b00-4892-ba00-a6a56f0361de · outbound

This paper cites On the entropy of language models in getting semantic from tokens.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models On the entropy of language models in getting semantic from tokens

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:15.029177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.577705Z digest=sha256:2d1706cb5675f44a76a5f50e6def8024167d45844374f91de590ab3336b81232

Observation 99f3d4a4-63b4-45a4-b8af-57f28d8c9084 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Evaluating Large Language Models Trained on Code

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.583159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.583159Z digest=sha256:78396e537cf44ce2509ebe5e8f35b66114235b8cac00452bb909e560da4b0b7c

Observation fbb67b4f-8283-428e-a768-e65ff7139b35 · outbound

This paper cites Advances in Neural Information Processing Systems 37 (2024), 86226–86242.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Advances in Neural Information Processing Systems 37 (2024), 86226–86242

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:15.009246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.588329Z digest=sha256:71ee7354f780be56abd77cc30aaee59c9cbb98a6a07ecedcdc8e5867a79d50d8

Observation 054900d8-8fcd-4289-8adb-ba16e784ed72 · outbound

This paper cites Nvidia a100 gpu: Performance & innovation for gpu computing.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Nvidia a100 gpu: Performance & innovation for gpu computing

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.990425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.594918Z digest=sha256:4c28f3e0846134f40f23bef96b5fd3b2512f205ec5265d28e8867857fcd22f95

Observation 74c27c97-03d4-4224-883c-4c6c176fcbe5 · outbound

This paper cites W., Sutton, C., Gehrmann, S., et al.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models W., Sutton, C., Gehrmann, S., et al

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.972225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.600193Z digest=sha256:89263099d374687fdfbd10fe9deeddb74fd6c5946a565ed1e37b35822a8c4dcc

Observation 11b0c632-31d9-43db-9df0-60dff021d1da · outbound

This paper cites Unified scaling laws for routed language models.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Unified scaling laws for routed language models

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.955648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.605893Z digest=sha256:3768542bd7aaa883b9eadb6c47175d96ef189f2a84d6666c470de111a12dd54c

Observation 47e1aba1-1411-4734-a441-fb0c8731d684 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Training Verifiers to Solve Math Word Problems

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.611689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.611689Z digest=sha256:63a5c0a332be343247326a6d7acacf7f7da17b00ef35bc4aae1604bb2b2f03e4

Observation 3d63a160-07f7-446b-a26d-ae2a40851224 · outbound

This paper cites J., Gonzalez, J.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models J., Gonzalez, J

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.937357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.617019Z digest=sha256:547272421a2d27ec82d6f6d837bc4e9ded68a67c74d30929e9c00b2eff4393e4

Observation 28cd6802-0e0e-4d37-8765-71c051e19b11 · outbound

This paper cites Increasing transformer token length with a Maximum Entropy Principle Method.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Increasing transformer token length with a Maximum Entropy Principle Method

Reference 13

Resolution
verified exact
local_arxiv, observed 2026-08-15T22:15:14.272768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.622247Z digest=sha256:62ee32d4d96db5c8c3e32503f3b685618a52ce3395974d7c7e317bf69ced1d6b

Observation 44e5dcae-d9db-4653-aafd-ccdfede57688 · outbound

This paper cites Graphrouter: A graph-based router for llm selections.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Graphrouter: A graph-based router for llm selections

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.918581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.627914Z digest=sha256:e39f3abf1a76c113d7b1843482d7347934e2cbf9e84ca8192dcd55994bd5da46

Observation f876072d-4cdb-4f27-853f-bd923e951340 · outbound

This paper cites {ServerlessLLM}:{Low-Latency} serverless inference for large language models.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models {ServerlessLLM}:{Low-Latency} serverless inference for large language models

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.901868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.632648Z digest=sha256:6ebf7a7e941653e97260c2488679859f760375ff96b0fdbad6be5ca08652e015

Observation c795fa38-6b7c-4592-8de1-5c8294cff007 · outbound

This paper cites The Llama 3 Herd of Models.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models The Llama 3 Herd of Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.637412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.637412Z digest=sha256:7cf53c6bdf647a3b81acd3994c91dd94cf41229306d861cb7b09c2aecfaa76bd

Observation da1d88a5-dcc1-4579-bea9-726441ed5dc3 · outbound

This paper cites In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24) (2024), pp.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24) (2024), pp

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.882826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.642920Z digest=sha256:75233a1981b90642f6e7c41927903b44b18bf51a6a75fc4aa1b4b391c5754a72

Observation 9a354ea9-a7f3-41ee-b45f-0613632006cd · outbound

This paper cites Specserve: Efficient and slo-aware large language model serving with adaptive speculative decoding.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Specserve: Efficient and slo-aware large language model serving with adaptive speculative decoding

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.647987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.647987Z digest=sha256:1c3a65208cd5bb2425d549936551465bb776fd2f312588de8f3755a208124650

Observation 57506a0d-7b31-45ab-be90-760a58573601 · outbound

This paper cites an unresolved cited work.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-15T22:15:14.862814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.652985Z digest=sha256:c3e8b48490d33f003fd50b2c41275a271b1d7fd1ab2a886c7a2915f684f7a649

Observation b4fc5202-ea58-4a94-86d7-83e88ba75fa7 · outbound

This paper cites an unresolved cited work.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-15T22:15:14.845396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.659048Z digest=sha256:d43c6c3e0fd25b277970b98f6ef226f538724eb57a28fa5f1c4678181554a194

Observation c85f4f96-ec80-4b5c-8a18-36a0533d44e4 · outbound

This paper cites Scaling Laws for Neural Language Models.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Scaling Laws for Neural Language Models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.664620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.664620Z digest=sha256:ff0fd7948cadc468c5d9d4315fc85d207b9f2a42fb954a24047b2c3620e1a57e

Observation 63c2c6a9-3775-4983-bcfc-232358a10a72 · outbound

This paper cites H., Gonza- lez, J.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models H., Gonza- lez, J

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.828587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.670542Z digest=sha256:27c214c180326309d29230b3cfa22bd559096789189b49e0fb3de5e9d3ab94ea

Observation 80794bdd-b602-4d3d-8d05-6805d9ac8e73 · outbound

This paper cites an unresolved cited work.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-15T22:15:14.808680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.676139Z digest=sha256:0a70b99368822e17f7108372629faab38fd65953669359dce7a63a8c207dd33e

Observation 03c90b20-eb62-403b-ac10-66239d09b33b · outbound

This paper cites In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) (2024), pp.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) (2024), pp

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.792041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.681405Z digest=sha256:0d6c2f6a5725be3f92ac23fdc33cd24a0fb6a64fceb732f9432dd6c5cc5ab715

Observation f546f64c-c898-48d4-bf16-cecf5f431917 · outbound

This paper cites Fast inference from transformers via speculative decoding.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Fast inference from transformers via speculative decoding

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.686186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.686186Z digest=sha256:36754383c499863f0d1fb1ef74cb411f4eef9b6ecdc0aa091fc259a98b79c4ca

Observation b2e63812-374d-4dc8-9e00-d9f8644c0db3 · outbound

This paper cites Static batching of irregular workloads on gpus: Framework and application to efficient moe model inference, 2025.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Static batching of irregular workloads on gpus: Framework and application to efficient moe model inference, 2025

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.763032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.691282Z digest=sha256:f1ebe83532d46fa6fbe4a44fde609c4377cc5911a9c627e28def5c999f146ae8

Observation 00425c87-dad2-4973-920f-b39b6da1dfc8 · outbound

This paper cites In International Conference on Machine Learning (2024).

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In International Conference on Machine Learning (2024)

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.743595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.696497Z digest=sha256:f242570edbb1019a8dd76763722618856ff3d1e98daa08e40ef71a2d7a47a429

Observation 8aab46b4-5e4a-4bbe-a148-bb81d92b6af3 · outbound

This paper cites EAGLE-3: Scaling up in- ference acceleration of large language models via training-time test, 2025.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models EAGLE-3: Scaling up in- ference acceleration of large language models via training-time test, 2025

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.726931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.701403Z digest=sha256:2ebbdc8449c92a0689f5b571d139c7d10e563b414280a6f815cc531f801a4646

Observation 0f9ab5f9-6cbb-49bd-a34e-65ac06638bbe · outbound

This paper cites AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.707025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.707025Z digest=sha256:ddcee032ee917a29b27fcac71c1d749b612294d04d1afa2b1e1c4b1e16ecba2a

Observation 3d83a165-af28-4402-96b4-3953b225a919 · outbound

This paper cites Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.711912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.711912Z digest=sha256:70a59fef1b27159053d64adba7ed3292bf9159d17b35bd893947fef1a3b6ad79

Observation 8cefd015-1403-487b-a0c4-3f0db079b6aa · outbound

This paper cites Parrot: Efficient serving of{LLM-based} applications with semantic variable.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Parrot: Efficient serving of{LLM-based} applications with semantic variable

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.708536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.717686Z digest=sha256:bd9acb9dad4f1bfd8608ac74021052efc05d2bb54f766a2cfdd18c1c8e67fb17

Observation e9fe6c4a-47e6-4876-b6f9-f274be228282 · outbound

This paper cites DeepSeek-V3 Technical Report.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models DeepSeek-V3 Technical Report

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.723164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.723164Z digest=sha256:32d92fb9271f85b83ac730276ca7e4584e80a592f1f45c9926a24f4eea8c07c3

Observation c2989215-92c3-4a70-8037-c845dcfddde8 · outbound

This paper cites In The Thirteenth International Conference on Learning Representations (2025).

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In The Thirteenth International Conference on Learning Representations (2025)

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.686809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.729212Z digest=sha256:b606a30f881fb7fd08a4e6c456ab8f352f3b6debb32c6ca29451bda065a7edfb

Observation 0d188986-b388-4c14-b1ef-744f74994c0d · outbound

This paper cites A., Xie, G., Zhan, J., Zhang, H., Hjálmt `ysson, G., and Greenberg, A.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models A., Xie, G., Zhan, J., Zhang, H., Hjálmt `ysson, G., and Greenberg, A

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.665357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.734325Z digest=sha256:dcb36897af74336012e4748959cbd20f344d8e339e9039e5ddc19102c891e06f

Observation cbdd3b13-c800-4b6f-96f9-632a2fbfd003 · outbound

This paper cites an unresolved cited work.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-15T22:15:14.642339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.740476Z digest=sha256:1d9d7fdbabf6c612b092ca60202b6374d5ca03754bd355271f52b2f6b96c44bf

Observation 929e9577-67e5-4aa3-bb8b-17e59335794b · outbound

This paper cites E., Kadous, M.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models E., Kadous, M

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.615755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.746940Z digest=sha256:2e6f641299ab7db398dfd98a4aa90404896c777a946156b56882738360c6b957

Observation 69e60518-c607-4f91-87c7-b2fcb5e1152e · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.752670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.752670Z digest=sha256:bbc12902466c6ae57d67c589dcb813b3d38e8e21a97607d5b166040f9786b17a

Observation 134d94a4-9a71-4a1a-8de2-3918edd1cbe4 · outbound

This paper cites Mooncake: Trading more storage for less computation—a {KVCache-centric} architecture for serving{LLM} chatbot.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Mooncake: Trading more storage for less computation—a {KVCache-centric} architecture for serving{LLM} chatbot

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.598715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.758219Z digest=sha256:3b3fa73300676484f89bcb4dcb0c116427f885c459090105d0836d5f3118620e

Observation 109e5710-3256-4ac8-8fde-fb1d9ac954f4 · outbound

This paper cites S., Jha, S., Kalbarczyk, Z.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models S., Jha, S., Kalbarczyk, Z

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.580875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.763812Z digest=sha256:c1b552338e37a06dbe3bd6b74d920e6efd660cc08233753bf3118e450caef6f6

Observation f33d1552-9d73-4d98-a5f2-64ffd0f1c1e6 · outbound

This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Language Models are Multilingual Chain-of-Thought Reasoners

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.770008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.770008Z digest=sha256:826bbe3f19b08b1dc45331662fa8ae45fbd8a5509ad1a7875b9d6bae1ac1ea30

Observation e425b137-2575-495e-9973-86f42dce87ac · outbound

This paper cites In Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles(2024), pp.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles(2024), pp

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.564202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.775595Z digest=sha256:4767fc2710d72194383bef8734debea963ceeccc78432b99e6bce5c047b856ed

Observation 6a6dc703-de01-4f34-ae88-a4ce4fb2e85b · outbound

This paper cites Llumnix: Dynamic scheduling for large language model serving.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Llumnix: Dynamic scheduling for large language model serving

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.546263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.780511Z digest=sha256:cc1bd3a28acd4dd94677720d5a69829bc2f2b41b9df471289f32497adcc5ab48

Observation e14f3436-8cb5-40fd-8527-d71aff84aa03 · outbound

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

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.786730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.786730Z digest=sha256:7cbe07858d7497e0aa2ea14f08b0f30560e8a19475b131158f6705b6f6e9947d

Observation 8a8beda3-dd0c-4dd6-b58d-2b3621bd4fc0 · outbound

This paper cites N., Kaiser, Ł., and Polosukhin, I.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models N., Kaiser, Ł., and Polosukhin, I

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.526139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.791983Z digest=sha256:deaf233d20168b07f721512a83628d5579b4ed06079d43a791e9a96f7725030f

Observation a004264e-896b-429b-9c36-1ce0ea5e3a8b · outbound

This paper cites In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations (2020), pp.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations (2020), pp

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.507776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.797021Z digest=sha256:ea39f8fbe076e290f05e1de32e1492ed7ed264dba9234f2b68a6b1dd4b1ff6b4

Observation 5fc0c6f5-5a40-40b9-b4af-56e9949e3cb1 · outbound

This paper cites Loongserve: Efficiently serving long-context large language models with elastic se- quence parallelism.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Loongserve: Efficiently serving long-context large language models with elastic se- quence parallelism

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.489109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.802740Z digest=sha256:2fc84e354218070f5f3d14ce0fea3d6c121278f7f38e1563fed5f0c1e36386d0

Observation f7782d39-c43a-4d1c-93e2-9c6abe52c1a9 · outbound

This paper cites Advances in Neural Information Processing Systems 37 (2024), 128082–128117.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Advances in Neural Information Processing Systems 37 (2024), 128082–128117

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.466002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.807607Z digest=sha256:a97960af0ff1f4b10dc7c5514e86db16ce01b4a9fe6107850ff6f5c50609a635

Observation 66bbdaa8-5bcd-4e26-850e-7403018ef09d · outbound

This paper cites S., Kim, G.-W., Kim, S., and Chun, B.-G.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models S., Kim, G.-W., Kim, S., and Chun, B.-G

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.447709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.812611Z digest=sha256:9f81da8aa8f8f53988b51328dfe43375b6c4f849017ebb36617803849148c2b9

Observation 51c3b9f8-a77b-4815-afb2-bc691f243a19 · outbound

This paper cites Fast and live model auto scaling with o(1) host caching, 2024.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Fast and live model auto scaling with o(1) host caching, 2024

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.430057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.817817Z digest=sha256:ca0179b98f4a0d9f66f7d27d20d57fc78744c3e0c0f268a2affe1589175b6039

Observation 6739893d-ff97-475b-91e0-401f09fa0b41 · outbound

This paper cites Leveraging Uncertainty Estimation for Efficient LLM Routing.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Leveraging Uncertainty Estimation for Efficient LLM Routing

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.822890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.822890Z digest=sha256:a7a02337fb643aa26b90f0a3ca1034de2c58f198d206885f955e460aec4d64e3

Observation 41c72e65-dc45-4332-8e6f-e4cbc9b76dab · outbound

This paper cites Judging llm-as-a-judge with mt- bench and chatbot arena.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models Judging llm-as-a-judge with mt- bench and chatbot arena

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.409915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.827969Z digest=sha256:009541142a751165c027d637fcdc94c58a0530af585aee52a8e42a6d5801f963

Observation c05f7756-4730-43c9-9071-9a9e784ab483 · outbound

This paper cites L., Huang, J., Yu, C.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models L., Huang, J., Yu, C

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.391163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.833773Z digest=sha256:8024ad8fd6857ea589b38ecd8522ee7d4fa10cfb9b67a1a051cc67b5724f9625

Observation 3471d54a-77c1-469b-b20a-0bd0201c21c2 · outbound

This paper cites {DistServe}: Disaggregating prefill and decoding for goodput- optimized large language model serving.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models {DistServe}: Disaggregating prefill and decoding for goodput- optimized large language model serving

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T22:15:14.371621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T22:15:13.840499Z digest=sha256:7cfe60d5f9908587809f0137a025cbf8bda18cebafeefd85fb094d1744f9132f

Observation f6701ae3-4171-4835-b23e-104270ec9493 · outbound

This paper cites A Survey on Efficient Inference for Large Language Models.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models A Survey on Efficient Inference for Large Language Models

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.845648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.845648Z digest=sha256:571db35d485ef64f4b0debe970452d54040b5fd5dcec0e5b6c5131b833675c87

Observation 9493b1f5-425f-4d97-b9d1-ed847f7de737 · outbound

This paper cites FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework.

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-15T22:15:13.851365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:15:13.851365Z digest=sha256:da17900a61e000c81564819bd3328720965464647074dd08ba22f07104b8e351

Pith citing papers

Observation 1cd74e9e-5057-4edf-ae45-d6f027a4af6e · inbound

SpecMemo: Speculative Decoding is in Your Pocket cites this paper.

SpecMemo: Speculative Decoding is in Your Pocket SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-08-15T20:56:29.575242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-15T20:56:29.078219Z digest=sha256:a71dfebd101c7deab09321c3e8e9dce0915d71ede2eec65aa4f50ff5d179da8c