Paper Citation Record · LEDGER

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

As of 6 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2605.10453.

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

pith.paper-citation-record.v1
2605.10453 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T04:20:10.699246Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

36 of 36 outbound references displayed

verified exact17
verified fuzzy9
unresolved0
parse uncertain0
malformed identifier3
metadata mismatch7

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 361ff772-ef36-4b9e-aa3d-446031e2b23d · outbound

This paper cites Fast Inference from Transformers via Speculative Decoding.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Fast Inference from Transformers via Speculative Decoding

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:52:00.384886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ccc5f5b2-3075-4cf4-a253-b8ac0304b7de · outbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-12T04:21:19.677392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 111d67bd-cf9a-4158-a49f-2dc6902fd25b · outbound

This paper cites Rest: Retrieval-based speculative decoding.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Rest: Retrieval-based speculative decoding

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.856446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5657564f-ea12-4736-b578-e4043d3aaa66 · outbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Break the sequential dependency of llm inference using lookahead decoding

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.853047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7d7e599d-4b35-4c9e-87e2-9b0f6cdb23ca · outbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:36:18.892007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ec8a8335-e233-480a-b314-c7a57435e7be · outbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.680951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0ed16580-b96d-4082-869a-f792164d386a · outbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 7

Resolution: malformed identifier; arxiv_id, observed 2026-05-15T00:15:49.524886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 573b0795-90f4-4be7-8532-f59e9039b5c7 · outbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.693734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a4fd9def-5d8d-422b-b785-148f6f9023d1 · outbound

This paper cites EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:52:19.804345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6ec53610-7ffe-44a1-bd5f-f8f61b07ac6e · outbound

This paper cites EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T18:52:19.804345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6c3762d7-199d-4325-926b-db67d973baf5 · outbound

This paper cites FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.662958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2ecbdda1-8021-48f8-8bc2-cae83ba80816 · outbound

This paper cites Speculative Decoding with a Speculative Vocabulary.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Speculative Decoding with a Speculative Vocabulary

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-20T03:19:15.112310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bcb265b0-e186-421b-9f16-781bd95d5efd · outbound

This paper cites V ocabtrim: V ocabulary pruning for efficient speculative decoding in llms.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding V ocabtrim: V ocabulary pruning for efficient speculative decoding in llms

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.626763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1409bf96-ab96-4cc4-8a3f-b89821a6a44c · outbound

This paper cites Balancing coverage and draft latency in vocabulary trimming for faster speculative decoding.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Balancing coverage and draft latency in vocabulary trimming for faster speculative decoding

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.618564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2e0e6631-e7b6-4ff8-9e67-7f9f6417692a · outbound

This paper cites CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.645759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation be687de8-f0b1-4852-9d11-a303af35853f · outbound

This paper cites Dynaspec: Context- aware dynamic speculative sampling for large-vocabulary language models.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Dynaspec: Context- aware dynamic speculative sampling for large-vocabulary language models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.649305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bf01861e-9a63-4e80-a209-10bcd944a482 · outbound

This paper cites LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-02T04:04:29.221763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b16d51d8-7c0a-4c41-ada8-f1a1730a9ec6 · outbound

This paper cites Out-of-Vocabulary Sampling Boosts Speculative Decoding.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Out-of-Vocabulary Sampling Boosts Speculative Decoding

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.669836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b9806f5f-c238-4107-8892-d544accaa9a3 · outbound

This paper cites Efficient softmax approximation for GPUs.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Efficient softmax approximation for GPUs

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.839758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 14c1fab1-8d0a-4d50-ad9a-f5a85696d92c · outbound

This paper cites Chen, Si Si, Yang Li, Ciprian Chelba, and Cho-Jui Hsieh.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Chen, Si Si, Yang Li, Ciprian Chelba, and Cho-Jui Hsieh

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.829456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b253cd08-1cc4-47b6-8741-005388a9ccd4 · outbound

This paper cites Adaptive input representations for neural language modeling.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Adaptive input representations for neural language modeling

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.833208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a3c2071e-fb99-4ad9-a2e1-d1c49e5bf3cf · outbound

This paper cites Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.659498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 66b08d96-c402-4cd4-bdd5-3e07b6f992f2 · outbound

This paper cites Tensorized embedding layers.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Tensorized embedding layers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.842967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6a750851-ae11-4c58-b212-d13fd462e4fb · outbound

This paper cites ALBERT: A lite BERT for self-supervised learning of language representations.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding ALBERT: A lite BERT for self-supervised learning of language representations

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.836430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4f7e45ae-12f3-4220-992a-24f501ebc9f8 · outbound

This paper cites Deep learning meets projective clustering.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Deep learning meets projective clustering

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.846107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c7b1500e-ab8d-493f-933a-5117d268b10f · outbound

This paper cites Slimpajama: A 627b token cleaned and deduplicated version of redpajama.Cerebras Systems.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Slimpajama: A 627b token cleaned and deduplicated version of redpajama.Cerebras Systems

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:36:39.849458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b6e6532a-12b7-4135-8d7b-1c00dc6bc8ec · outbound

This paper cites The Llama 3 Herd of Models.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding The Llama 3 Herd of Models

Reference 27

Resolution: malformed identifier; local_arxiv, observed 2026-05-12T04:21:19.641647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 20b2a1a9-a07b-4494-9bca-04b5198d9c2c · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding gpt-oss-120b & gpt-oss-20b Model Card

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T04:21:19.634590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 691cbfa7-faf3-4961-826e-ec02f3568c06 · outbound

This paper cites Qwen3 Technical Report.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Qwen3 Technical Report

Reference 29

Resolution: malformed identifier; local_arxiv, observed 2026-05-12T04:21:22.770749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8dbe3302-ad9a-498f-98f2-0913806169ba · outbound

This paper cites Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.630771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 66250d86-6cf7-441b-a44e-60c3a925051a · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T04:21:22.774995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f9876da7-1886-42f3-ba78-f6bed18f952f · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T04:21:19.666003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8bfe7611-276f-46b1-97da-cc5fa3eb11c4 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Evaluating Large Language Models Trained on Code

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-12T04:21:22.757526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f41f0926-f7e4-46f6-9ea6-7e8609cc10be · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Evaluating Large Language Models Trained on Code

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T04:21:19.622747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27c170bd-f72f-43c9-8b47-01c502d76fe0 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Training Verifiers to Solve Math Word Problems

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-12T04:21:22.762802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9216f5a7-4bd7-4700-9792-53001493ebf5 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Training Verifiers to Solve Math Word Problems

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T04:21:19.655283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.