Paper Citation Record · LEDGER

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

As of 19 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 2 inbound Pith citation observations for arXiv:2412.00061.

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

pith.paper-citation-record.v1
2412.00061 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T13:15:07.306486Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:16:26.218271Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T19:02:34.639740Z

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy6
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7dafc0a5-e07b-4b38-9f4c-963008ed5712 · outbound

This paper cites GPT-4 Technical Report.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.134891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81e64fd7-4189-4b95-a1f8-8a6d545713fe · outbound

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.141779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39c6ce24-f594-4281-973d-e1b8eceb7b43 · outbound

This paper cites Medusa: Simple framework for accelerating llm generation with multiple decoding heads, 2023.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Medusa: Simple framework for accelerating llm generation with multiple decoding heads, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:15:07.802892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cdc6218a-69f1-4979-98a0-ea0fcf3165cc · outbound

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Accelerating Large Language Model Decoding with Speculative Sampling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.154072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb37119-5ca2-498f-9683-4fe5acd61444 · outbound

This paper cites Cascade Speculative Drafting for Even Faster LLM Inference.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Cascade Speculative Drafting for Even Faster LLM Inference

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.159423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec52fe2a-7e90-4c52-a0e6-0d1e81cbad69 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.165281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb13f95-7222-43db-8910-0a07a5aa976d · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.170268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 680c2458-c6e9-49e8-bac1-419f3190087c · outbound

This paper cites Tutorial on directed acyclic graphs.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Tutorial on directed acyclic graphs

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:15:07.772628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation beed94b1-721e-44ad-8974-102fac87eac9 · outbound

This paper cites Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.183111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746dfe29-8e6b-4a38-a806-c19cbc1ca527 · outbound

This paper cites SPEED: Speculative Pipelined Execution for Efficient Decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration SPEED: Speculative Pipelined Execution for Efficient Decoding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.188194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67459f86-ae2a-4eef-a242-e0fb2c7f3ad4 · outbound

This paper cites Mistral 7B.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Mistral 7B

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.201980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e41ad1c-e367-4eed-a1f7-21f74b60999f · outbound

This paper cites Fast inference from transformers via speculative decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Fast inference from transformers via speculative decoding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.207424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 035dd2d0-7333-48d4-8ba3-e175db4f4d79 · outbound

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.213417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 139f8768-1ac8-486b-a60b-659023c6dd8d · outbound

This paper cites SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.218014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b955a8cc-9cb4-4edf-b883-f1225addf738 · outbound

This paper cites Accelerating LLM Inference with Staged Speculative Decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Accelerating LLM Inference with Staged Speculative Decoding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.224514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcf09a45-24f9-42ea-aa36-08e6cec69b61 · outbound

This paper cites Insertion transformer: Flexible sequence generation via insertion operations.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Insertion transformer: Flexible sequence generation via insertion operations

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.230200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8554d824-62b3-4d4b-a860-74ce9a8650a1 · outbound

This paper cites Blockwise parallel decoding for deep autoregressive models.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Blockwise parallel decoding for deep autoregressive models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:15:07.713516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f7555fba-55e2-4eb3-9abc-3605e48fd5ec · outbound

This paper cites Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.240855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a3c2dd-d6ee-4b52-b306-a8a8358e1e58 · outbound

This paper cites Spectr: Fast speculative decoding via optimal transport.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Spectr: Fast speculative decoding via optimal transport

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.245355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69cd8bde-5543-4faa-8d6b-5828699f8564 · outbound

This paper cites An introduction to conditional random fields.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration An introduction to conditional random fields

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:15:07.682407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e5fb8e5f-0bc6-472f-9433-e9c514a86e46 · outbound

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration LLaMA: Open and Efficient Foundation Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.256088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74eb00b7-fb34-424d-898d-79eeedc215a4 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.262618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b351093e-64fc-4cbd-a61f-1569b67f3936 · outbound

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:15:07.668268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d116a5fe-8de5-42a1-9943-686b508e1d1d · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.274460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeb6f735-149c-4e40-895f-ca6eae19d0ba · outbound

This paper cites Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.283186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0e5002c-af63-483c-9901-77ee3353e1d0 · outbound

This paper cites Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.288948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8a9214b-1cd2-4e06-881f-14e16d536fba · outbound

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:15:07.652003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e8bcaf73-917d-478c-8fad-6b701a3a0a92 · outbound

This paper cites DistillSpec: Improving Speculative Decoding via Knowledge Distillation.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.306486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation dfaa0113-e027-4ed0-9e7f-fb27dead30ad · inbound

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs cites this paper.

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:16:26.218271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1fd930-b4d6-41aa-ae7c-cadfb9313ffb · inbound

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation cites this paper.

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

Reference 112

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:34.641097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.