Pith. sign in

Paper Citation Record · LEDGER

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

As of 15 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 12 inbound Pith citation observations for arXiv:2501.19309.

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

pith.paper-citation-record.v1
2501.19309 v1

Coverage vector

measured 64 of 64 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T20:43:28.734650Z

measured 76 of 76 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T22:28:20.436274Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T12:44:39.368757Z

Reference resolution

64 of 64 outbound references displayed

  • verified exact1
  • verified fuzzy15
  • unresolved48
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4085d09d-d9cd-4446-92c1-c8f5c776d3c1 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.519350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.519350Z digest=sha256:c32e643f5479f0af10a2f661ddd544c5685e1c7af3096a9fc2cbfe2e53f30cb8

Observation ff6e64dc-7880-481d-bb8e-ca5b7fe73c9e · outbound

This paper cites Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.524309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.524309Z digest=sha256:6130135b44ae92f6d144d308e7ed8f365cfd60b9a8f4f47360eb7e1ea0ab363a

Observation 10b50b8f-8441-4d9e-b29f-1bbe6c521c1a · outbound

This paper cites The pitfalls of next-token prediction.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment The pitfalls of next-token prediction

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.528271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.528271Z digest=sha256:006c3e03f906ef36e2baab37b90cfb74a5996b7a2008bb226ea4866cb4549747

Observation 55c28658-f78e-4556-8a76-5f94d086f314 · outbound

This paper cites Speculative Streaming: Fast LLM Inference without Auxiliary Models.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Speculative Streaming: Fast LLM Inference without Auxiliary Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.532056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.532056Z digest=sha256:63ae87659e7cee935f9d204060572f5f70f0e0c85896d8daccf3a71fbc5c6696

Observation 87170062-8f58-4cac-8d72-1a3eaf5812d3 · outbound

This paper cites Discovering latent knowledge in language models without supervision.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Discovering latent knowledge in language models without supervision

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.535887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.535887Z digest=sha256:d3177f9daad9b9bb2e8a53303d308a603854a0ffd6d23a150d8354e1721e27a5

Observation c876d3d8-4df1-48fa-8efc-3aded5acc9e1 · outbound

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

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.551801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.551801Z digest=sha256:43c98f87d5903893793643eed13292b19aa56addf3f9ede7e894b973b9f96a3e

Observation 16e0a974-5bd9-448f-abcf-37e93b414229 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Accelerating Large Language Model Decoding with Speculative Sampling

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.610251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.610251Z digest=sha256:a579faa3c30cbcb8b9711960d482900a751520aedf0300cce00149718965e665

Observation 1db3e9d4-6718-4a8c-ad6a-189272ad76f0 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Evaluating Large Language Models Trained on Code

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.650005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.650005Z digest=sha256:a556e0333e682c7b847c9fa2b3d2c2c0662b429bf73fe0d82e5b083cde562faa

Observation ca67f8bb-bea2-4a3b-84c2-8dc99c3db2fc · outbound

This paper cites Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.709855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.709855Z digest=sha256:cc0046b717c5c7df39bb55054fcaa451bdb1b96cad9ff6884dfc63631e5f345f

Observation 190d0c23-5cdd-4d64-b8a4-98a542289930 · outbound

This paper cites Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.756947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.756947Z digest=sha256:be84983eb28c19fc83327a03ec7598802ff0575fb275978edee396af3b6731f8

Observation c298ae2c-7085-4a43-8f2c-a299f3ff56e6 · outbound

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

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.836353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.836353Z digest=sha256:2c139ef4ce065cdc5d0046e76b59e51582792247b88662665e7884b31006616f

Observation 3999321b-6dda-48b1-bba5-c849863cc8bc · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Training Verifiers to Solve Math Word Problems

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.879057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.879057Z digest=sha256:5cec30f534cf6f60dd06b1aa4e6b43c5bf120d712b0ad696ba9d93802b1c788f

Observation e45f259b-6e12-40a1-8e16-37b41703cf0c · outbound

This paper cites Glide with a ca PE : A low-hassle method to accelerate speculative decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Glide with a ca PE : A low-hassle method to accelerate speculative decoding

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.822854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.909643Z digest=sha256:3ec1efcf971f4adfb35e4f3e874cacca6d62f29da85a7e6c2a6468b60357ca40

Observation bb0ea73b-95d2-4120-9a12-19e8467f46f6 · outbound

This paper cites The Llama 3 Herd of Models.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment The Llama 3 Herd of Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.939138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.939138Z digest=sha256:cb1d16adc13a9a36e724706d796e80442b9f15544fcb7603840d533ad6a6c93f

Observation ba4270c6-e57e-4e65-aa96-42bbccb38737 · outbound

This paper cites L ayer S kip: Enabling early exit inference and self-speculative decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment L ayer S kip: Enabling early exit inference and self-speculative decoding

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.812069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.945470Z digest=sha256:9cf5a92dcd6d213e1cc599ea587dd43c281fa974056dfd2bbe87b5b06486bc5a

Observation eb551bbe-eef1-45f5-b5dc-1bcec5a7164d · outbound

This paper cites Break the sequential dependency of LLM inference using lookahead decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Break the sequential dependency of LLM inference using lookahead decoding

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.948547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.948547Z digest=sha256:37c762b0d0e94344df4a1162e7d7854056bbf62b7fe7f6a89f3880dfa35dfddc

Observation 39c6ac17-c56a-4bf1-ad89-4419a0a2557a · outbound

This paper cites Better & faster large language models via multi-token prediction.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Better & faster large language models via multi-token prediction

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.795489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.951685Z digest=sha256:c012d3ecbe1930fb2780c18f2a928e3eb643d1f6968a722b3ee3e489ad7bb0af

Observation 3021abbf-f1fd-40b9-a8cb-9690e2669d75 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.955146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.955146Z digest=sha256:50daddebcf534865b94d14777c3f20957bcafaf9ae4003bfa1817bbe88789501

Observation fd68835e-7fd4-4d86-99c1-f4bfaabc89c9 · outbound

This paper cites Language Models Represent Space and Time.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Language Models Represent Space and Time

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.959554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.959554Z digest=sha256:fcec00e9be3a33190a51155e00ed0b882230a5703c3dd5d6219b4d783d9e78aa

Observation b31d5634-06d0-4302-be0f-c1fddc30002b · outbound

This paper cites Measuring massive multitask language understanding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Measuring massive multitask language understanding

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.963228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.963228Z digest=sha256:43df0aa35b384220af80dd3d70647737c502ea1bc160af9c819fa797e8e3771c

Observation 31bd3a57-1db6-43b5-9b81-8f0e36b02591 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Training Compute-Optimal Large Language Models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.966094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.966094Z digest=sha256:114e5e26c68b20963ab3269481ac332fc51a5b2d1e635bd6e8f100484027e19c

Observation 0af5de14-086b-4b91-b057-27e1ecdf9258 · outbound

This paper cites SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.969502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.969502Z digest=sha256:fbb715e01e654c623986db55cf4e4f86a59114440c966f4d1323ebe712c26a55

Observation f977499a-6d5f-448b-aef5-342602f61ca0 · outbound

This paper cites Data movement is all you need: A case study on optimizing transformers.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Data movement is all you need: A case study on optimizing transformers

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.753585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.972616Z digest=sha256:266aaa799ff22df23ad62d82d8d52d4dbf8a3679dc84eb5872c80da86394e711

Observation 02a1b503-4b37-4677-b629-417d672ecc9c · outbound

This paper cites Scaling Laws for Neural Language Models.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Scaling Laws for Neural Language Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.975402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.975402Z digest=sha256:9992cdbb76855982dd8ae409fffe0d419b1a588b6ebabc3d4f35d618635e094c

Observation bfff92e5-596d-4181-b9cc-989ba1f5d2f9 · outbound

This paper cites Mahoney, Amir Gholami, and Kurt Keutzer.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Mahoney, Amir Gholami, and Kurt Keutzer

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.709939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.978768Z digest=sha256:0c8b7835abe0dbb65546af6453c040b08ba0567fdd84fb435763fe88d980c0fe

Observation e708a928-0446-42db-ab6d-f6f6d976d42c · outbound

This paper cites Fast inference from transformers via speculative decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Fast inference from transformers via speculative decoding

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.667175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.982927Z digest=sha256:21be03a2fbcc3f279bf72280513ea8ac4d669eaf2a6000eae3a4c4e0041d94e5

Observation abcaca6a-ddd8-4af9-b121-d05ff2e181c5 · outbound

This paper cites Eagle: Speculative sampling requires rethinking feature uncertainty.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Eagle: Speculative sampling requires rethinking feature uncertainty

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.626812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.985984Z digest=sha256:fa63c5ab0919f8200581c0389e7cfbdb046b5dc2873cad626725bdfef8e501d7

Observation 261d9423-7a29-4b63-bf29-58f284d4ae6f · outbound

This paper cites EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.989780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.989780Z digest=sha256:507bb15e536da35089909708c3796d3ff650a3fad2bb62d1ad84674bd97fb77d

Observation 8772975c-3958-4b1b-a578-ac2f2a40cc9d · outbound

This paper cites Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.993414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.993414Z digest=sha256:756c478fa4fc75506037b258c3b4a44a8bd12a22fdaf0c22e2886a690d1663d8

Observation e0205688-5e0c-441e-bfec-f1352adf9268 · outbound

This paper cites Speculative decoding via early-exiting for faster LLM inference with T hompson sampling control mechanism.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Speculative decoding via early-exiting for faster LLM inference with T hompson sampling control mechanism

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.590110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:27.996795Z digest=sha256:8d2a88a16e1f7f102a9425ad82a3a42e4be00ead166a5fcc3ff3a4c5f5524da6

Observation fed1400d-ee3d-4922-9a7b-9836d09322d5 · outbound

This paper cites PEARL: Parallel Speculative Decoding with Adaptive Draft Length.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.999754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.999754Z digest=sha256:4d8c409e4f3d1c565f7fc7f07acc33ee3f1c239e653d2658f1ac8fab2f54ab78

Observation f3d2788b-de83-4c00-a3cf-05338503fec7 · outbound

This paper cites Online Speculative Decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Online Speculative Decoding

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.003596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.003596Z digest=sha256:7e21fb8f0e50fad57a0828cad23c80849e4fa81f5887b080577bff25d6cac609

Observation b7ae0ba1-fcfd-46d4-a896-599cfa787bc6 · outbound

This paper cites Decoupled weight decay regularization.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Decoupled weight decay regularization

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.054690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.054690Z digest=sha256:ebf8bbbaba622292a7f28f1b8dad1a4c6a66082f57f2db29a2d8b439711c83bc

Observation d1a7d43c-d04b-4852-b709-a9625c8da2c6 · outbound

This paper cites Specinfer: Accelerating large language model serving with tree-based speculative inference and verification.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Specinfer: Accelerating large language model serving with tree-based speculative inference and verification

Reference 34

Resolution
verified exact
arxiv_id_nonexistent, observed 2026-08-09T20:43:29.185262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.105162Z digest=sha256:37d123caf647edcc3006f90a3f4c0d8387390e800d3f4d5b28fca86d6b9fedad

Observation 725bbda9-89f9-4ac5-aa56-606694e8d046 · outbound

This paper cites PaSS: Parallel Speculative Sampling.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment PaSS: Parallel Speculative Sampling

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.177798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.177798Z digest=sha256:701c016d466f23915d0c7951a4b71546aaba0c4449bfb7147727c9b6e07a5b28

Observation 60479fae-7488-42c3-a4c2-2e61457f356a · outbound

This paper cites Llama 3.1 performance with medusa.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Llama 3.1 performance with medusa

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.573670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.293859Z digest=sha256:f8c31cf907d80ae0e447151f7f1a23084402acb0c62bb4faa89fd1c2a889fd4c

Observation ec58d14a-6e57-41cc-8a3a-09120d18eca4 · outbound

This paper cites an unresolved cited work.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.387784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.387784Z digest=sha256:b13377ce531415c2fa6b2c5976181090a92dd8b0f249e1e688d0a9c0df6060b8

Observation 2cb80fcc-ddcb-42f0-86ab-b5edae073651 · outbound

This paper cites Efficiently scaling transformer inference.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Efficiently scaling transformer inference

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.438304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.438304Z digest=sha256:7f655e4c1d1b694887bc7a61cd8f770bb15d92972c625249b249a7ef5fc20ef0

Observation abc45cca-d3dd-4a57-bdef-27af896d9ff6 · outbound

This paper cites gpt-fast.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment gpt-fast

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.550639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.467066Z digest=sha256:d1299650c47aa6d25bc59efb40861134ecf0528c3055a182a088f53df19f785a

Observation 473d1100-7038-4988-a4e2-c067c5e5c736 · outbound

This paper cites Language models are unsupervised multitask learners.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Language models are unsupervised multitask learners

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.473110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.473110Z digest=sha256:e653af321d0823e0e432b46667c999e5c47eecdb8e10cafda5a94bd75c63cf68

Observation 5e1a98bc-3ffd-4de5-9ae5-2d0ababc35ef · outbound

This paper cites Tandem transformers for inference efficient LLM s.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Tandem transformers for inference efficient LLM s

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.534602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.477671Z digest=sha256:db32b716fd5467533a8c8d86e2cd3adf21392b0883a6fb035ccdaa37ee3c0070

Observation 5a1cb4b6-1052-440b-ad5c-e186df94a3e4 · outbound

This paper cites Accelerating transformer inference for translation via parallel decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Accelerating transformer inference for translation via parallel decoding

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.483794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.483794Z digest=sha256:0710617b3245720788d4abfc58e982b45ff54e59e49017e814331c0e865d49d0

Observation 400fe411-f5e9-4910-bb88-ebce362a89a0 · outbound

This paper cites Improving the compositionality of word embeddings.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Improving the compositionality of word embeddings

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.522273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.488540Z digest=sha256:ef47647a5bf71e11976225df9d05cb6eef6f279dbe6766791abaa292cae69036

Observation 13641fa4-4ff8-4dba-b738-6703697e8889 · outbound

This paper cites Tran, Yi Tay, and Donald Metzler.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Tran, Yi Tay, and Donald Metzler

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.511507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.491614Z digest=sha256:fbf50e7963ce1fec265638564d61ad3b793715f9d1bd6de010205f6a7fb06616

Observation 0cfebaf8-d68b-4bf0-8cd2-d408d55bb647 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Fast Transformer Decoding: One Write-Head is All You Need

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.494627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.494627Z digest=sha256:cdeef2b5dec602c5569ae5a9dd0aeced504486201c27098379930caab3c7e01a

Observation 350c8e18-f0d9-42cd-913f-87378f3e4861 · outbound

This paper cites Shazeer, and Jakob Uszkoreit.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Shazeer, and Jakob Uszkoreit

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.497829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.497829Z digest=sha256:91992ca3f52ff52f70f186a40a8aed36cf8cad92e7cb94f3c01e85e7ef94946c

Observation bc9aaf7a-57f2-4909-bbab-b66667f2e910 · outbound

This paper cites Instantaneous grammatical error correction with shallow aggressive decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Instantaneous grammatical error correction with shallow aggressive decoding

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.500724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.500724Z digest=sha256:00e6a219595f71b91b17454771b32b4cb4fba67a0bd81b02cdff706ae6da426c

Observation 718cc568-f13e-4b7e-9d39-bbbeb7a34424 · outbound

This paper cites Hashimoto.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Hashimoto

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.504394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.504394Z digest=sha256:82da3d850273e4ce1fb40c6387b213d5b59f44767fb32c3e7dcd21717051ef46

Observation 204da08b-2e9e-4956-8776-8b5c5670221a · outbound

This paper cites LLMs cannot find reasoning errors, but can correct them given the error location.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment LLMs cannot find reasoning errors, but can correct them given the error location

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.507471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.507471Z digest=sha256:0c53ed0ac617d70296bd26e500fa5f46e7e2025eccce8358e9d8c6c97f223e93

Observation f7c6d8c8-439b-4aff-b871-54f52da772a6 · outbound

This paper cites A Language Model's Guide Through Latent Space.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment A Language Model's Guide Through Latent Space

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.511350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.511350Z digest=sha256:4bafe796151fb0f951fdf7e0b379268368949f92724d4144d01dba05c2cffa74

Observation 0bf13d17-b035-4d0e-b085-97a300260310 · outbound

This paper cites The Mamba in the Llama: Distilling and Accelerating Hybrid Models.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment The Mamba in the Llama: Distilling and Accelerating Hybrid Models

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.514872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.514872Z digest=sha256:65037a4db8c23af7998d14ffe6efa7435965ccfd8371202838e1b2dae5d6f104

Observation 2a0c556c-fcdc-4b3f-9cf1-b600e05fe148 · outbound

This paper cites Accelerating Production LLMs with Combined Token/Embedding Speculators.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Accelerating Production LLMs with Combined Token/Embedding Speculators

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.518610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.518610Z digest=sha256:93c748d74b1b630cdc7035b097477e0ec612b3d8a09288d05c30c9fedb436efd

Observation c29d703e-8352-4dac-b268-cf46e51f4e31 · outbound

This paper cites an unresolved cited work.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Unresolved cited work

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.521974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.521974Z digest=sha256:0fd5b314e28cde93dcb9442e42565c27e1e669054fc3c3ee3c736d5ee4644557

Observation 40428115-926a-40cf-8062-43eedb9db1aa · outbound

This paper cites Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.524767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.524767Z digest=sha256:995b9814c643a423bf74b45ab78abdeebe7b59022ebb6d23b3f904df763c8c00

Observation ace799fd-7be1-4cd7-b1d2-00bc560b6dae · outbound

This paper cites Recurrent Drafter for Fast Speculative Decoding in Large Language Models.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.528369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.528369Z digest=sha256:18ebd6f03be70ffddae67cab53f72b4f472362daaf360c87f521456e4426940e

Observation 0b0468ba-369f-41a3-ac9f-ce1ead98bce4 · outbound

This paper cites Root Mean Square Layer Normalization.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Root Mean Square Layer Normalization

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.531501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.531501Z digest=sha256:517582c5b9e5b466865ec14938d5c48aeb8cfada43c53c32be3b833304c0c2e1

Observation 7626693c-57c3-4af5-86ed-5f470843f900 · outbound

This paper cites Draft & verify: Lossless large language model acceleration via self-speculative decoding.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Draft & verify: Lossless large language model acceleration via self-speculative decoding

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.479924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.534899Z digest=sha256:2c9d35f6328ec53612b684739ee5a8ed79f76f4286196921386b18dc5cba15ed

Observation 37833982-fe08-45f2-b94e-0cff7d729ba8 · outbound

This paper cites Gonzalez, and Ion Stoica.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Gonzalez, and Ion Stoica

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.538446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.538446Z digest=sha256:4f1c54005a26411fdd994e8eb085f7cbd3d9ad9713c70bfad3346131dd2d0eb9

Observation 79a881e5-f4bf-434a-89fd-089bf61636b2 · outbound

This paper cites Distillspec: Improving speculative decoding via knowledge distillation.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Distillspec: Improving speculative decoding via knowledge distillation

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T20:43:29.446153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-09T20:43:28.541874Z digest=sha256:45c91142b7a6ed30a8c3e7ccf8d3cd4c61227efe475d8990b4b12ccf95dc8767

Observation f0d8bf31-375d-4e86-90df-01217e8b2b3c · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.565306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.565306Z digest=sha256:a7fd0595b105468a4dbccb28422288d321fc4c295bb90df44eec407647883eee

Observation 624d028e-9ad4-4f15-bf80-7333b461bf48 · outbound

This paper cites write newline.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment write newline

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.601479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.601479Z digest=sha256:771c44cf6b36ee97e4742b0993f3be134d87f9f75664b6918b1f21c7bc6b3b85

Observation 85b10665-dda6-4336-a79c-b42103354d49 · outbound

This paper cites @esa (Ref.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment @esa (Ref

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.640787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.640787Z digest=sha256:f3bc5a14bdfac8eb2e525fa83f75d694b50447c5ec8268cb4ebe260713ab552f

Observation ba9bbd93-702d-4446-8cab-b6a8d28f87f5 · outbound

This paper cites an unresolved cited work.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Unresolved cited work

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.692051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.692051Z digest=sha256:f1a398e13be9e518708b70af34a718933c8c4609fb8055d541232e616de2b8ca

Observation 8c4be64e-a556-413f-a2d2-2600482e91c6 · outbound

This paper cites an unresolved cited work.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Unresolved cited work

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:28.734650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:28.734650Z digest=sha256:41ac15dd4f88d4aa48fb694270bffb6f12c154d6651b2967e298845330e22d11

Pith citing papers

Observation 1bbf85ee-3856-4f48-9473-503cbd0f3d76 · inbound

Speeding up Speculative Decoding via Sequential Approximate Verification cites this paper.

Speeding up Speculative Decoding via Sequential Approximate Verification Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-08T22:28:20.436274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T22:28:20.436274Z digest=sha256:3c8359a1662aa633ff256daa99e8d199a94c4bbae60466eb906d31e74cb86b91

Observation ad526306-0027-4d71-8a2f-400985c13325 · inbound

Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding cites this paper.

Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T14:32:40.716499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T14:32:40.716499Z digest=sha256:e8fcb3b53d297f06cc6a76e61c29960f454b64a1551276597af124b45d7c54de

Observation 1888de04-2769-408e-b941-e8efb4a61819 · inbound

POSS: Position Specialist Generates Better Draft for Speculative Decoding cites this paper.

POSS: Position Specialist Generates Better Draft for Speculative Decoding Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T11:04:15.672766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:04:15.672766Z digest=sha256:81f579e7ad48b7b40e0a98758ce36b93945028b15af810cc24d4075b8719c0a9

Observation 2c564df3-6203-45b1-8ebc-7fbf0db78e40 · inbound

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation cites this paper.

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-19T06:57:08.105128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-05-19T06:53:02.744567Z digest=sha256:83dfd8b73e2eca8c87586cb1063e8cc5761d86c8f1df5da9fb95b91f9f2f76a7

Observation 6f9c87b5-2a5a-4ec6-963e-c13f54e73fc4 · inbound

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation cites this paper.

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-18T03:20:48.614868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-18T03:20:35.021120Z digest=sha256:b7e24e42c052a77e3b9a8a8ac69258576b792d7469b84b4a7d9115995b72d402

Observation c46c2991-c572-4211-b15b-d31f89d9ab5c · inbound

Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match cites this paper.

Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-17T05:09:03.775841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-17T05:07:11.466066Z digest=sha256:c7cb13c45af853b14cf469d3f946b2a9a0ec9be181617bab6b7f75c0bb1abd9a

Observation 8ea66bec-d4a3-4616-9959-a307d3605a9e · inbound

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference cites this paper.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-05-10T12:25:22.830033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-10T04:33:28.537449Z digest=sha256:48fa8cc2175b3c22a9a7b2e91b87bc172802320e26c0d3bb7e0edfba6e58f002

Observation 2b2d14f1-f2c0-47f9-bc9a-e7c637bada05 · inbound

SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission cites this paper.

SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-12T00:31:17.297396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-07T15:12:12.450979Z digest=sha256:c28f49575db5ee54fb13568b00783a53e59258eeffb62fc4eb7091b3c23bd341

Observation a15d5a44-1014-483b-864b-a95b020f1820 · inbound

Beyond the Target: From Imitation to Collaboration in Speculative Decoding cites this paper.

Beyond the Target: From Imitation to Collaboration in Speculative Decoding Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T12:44:39.370575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-30T12:38:24.522899Z digest=sha256:900058bfa4f1d7ec243f1987efc27b88b7c3c3175a7fae1aa5efdf1da2046ae5

Observation 33de48c3-9d25-490a-b53f-f169bdebecc4 · inbound

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting cites this paper.

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-06-29T08:53:15.829133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-29T08:51:11.662084Z digest=sha256:29736ccbcd1cbd2902e51d61fe47882865fb0d25b5c38995550513459a70f03f

Observation 108b1706-daa3-4a9c-8c42-c3313cd2b39a · inbound

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting cites this paper.

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-14T10:09:31.872801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T10:09:31.872801Z digest=sha256:2e274748407d11ace387b699a718e0d51c1871486619b179c8098873b11efde7

Observation 1cf89e8e-1fce-429d-825a-2b827c7bd4e8 · inbound

Adversarial Prompts for Acceptance Collapse in Speculative Decoding cites this paper.

Adversarial Prompts for Acceptance Collapse in Speculative Decoding Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T06:43:34.620346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:43:34.620346Z digest=sha256:9a78ce9711b854161bc79d2146e4a623dd5213c396cb4fb918234a0248a965bf