Paper Citation Record · LEDGER

MineDraft: A Framework for Batch Parallel Speculative Decoding

As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2603.18016.

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

pith.paper-citation-record.v1
2603.18016 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:14:51.048500Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a69c6223-3e02-438f-828d-83bc75e5164b · outbound

This paper cites write newline.

MineDraft: A Framework for Batch Parallel Speculative Decoding write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:46.600284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fe7abec-fc54-4930-b95b-570e5b69389c · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

MineDraft: A Framework for Batch Parallel Speculative Decoding SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:46.669096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3bce2f3-f5d4-45bc-8f8f-7d3d622eb094 · outbound

This paper cites Sharegpt dataset.

MineDraft: A Framework for Batch Parallel Speculative Decoding Sharegpt dataset

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:46.786173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b59e4c8-dbc5-4275-9cc0-58022c554d7d · outbound

This paper cites D., Chen, D., and Dao, T.

MineDraft: A Framework for Batch Parallel Speculative Decoding D., Chen, D., and Dao, T

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:46.911164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90208bc0-7082-4ed5-9efb-46549c373407 · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.037475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc5af93-b56f-45c4-b4d8-8584ea99e97d · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

MineDraft: A Framework for Batch Parallel Speculative Decoding DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.147459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a042fb18-1d7f-4ee5-840e-dc4913762615 · outbound

This paper cites The Llama 3 Herd of Models.

MineDraft: A Framework for Batch Parallel Speculative Decoding The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.254920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdba3d89-b08e-48d2-ae5b-0b62c228a920 · outbound

This paper cites an unresolved cited work.

MineDraft: A Framework for Batch Parallel Speculative Decoding Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.407048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e33df120-8630-4d14-b205-c7a1738320fe · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding Specserve: Efficient and slo-aware large language model serving with adaptive speculative decoding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.526576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75ebd1ac-313e-4d96-b7ed-013763a93896 · outbound

This paper cites Transformers v4.53.3.

MineDraft: A Framework for Batch Parallel Speculative Decoding Transformers v4.53.3

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.624918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc54fd00-c9f8-43a8-a85e-b2442afe863d · outbound

This paper cites ibnzterrell/meta-llama-3.3-70b-instruct-awq-int4.

MineDraft: A Framework for Batch Parallel Speculative Decoding ibnzterrell/meta-llama-3.3-70b-instruct-awq-int4

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.739237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a656f7-5fc2-4da8-a191-4c388593195e · outbound

This paper cites H., Gonzalez, J., Zhang, H., and Stoica, I.

MineDraft: A Framework for Batch Parallel Speculative Decoding H., Gonzalez, J., Zhang, H., and Stoica, I

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:47.913177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3876205-edbf-4a5c-afe9-93f9f1261392 · outbound

This paper cites Fast inference from transformers via speculative decoding.

MineDraft: A Framework for Batch Parallel Speculative Decoding Fast inference from transformers via speculative decoding

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.072409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4947ebe-87da-4ed8-90e7-abb46008b96a · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding EAGLE : Speculative sampling requires rethinking feature uncertainty

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.196174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad033fcc-896e-44f6-b886-6ccb33468e56 · outbound

This paper cites EAGLE -2: Faster inference of language models with dynamic draft trees.

MineDraft: A Framework for Batch Parallel Speculative Decoding EAGLE -2: Faster inference of language models with dynamic draft trees

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.356425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f8f9bde-28a3-49b5-bc53-db2b10fb0651 · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.491243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6722a6bf-1307-4619-a1e6-304ebba110c7 · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.629742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d534511e-9e55-458b-a9dd-25cf9b231862 · outbound

This paper cites PEARL : Parallel speculative decoding with adaptive draft length.

MineDraft: A Framework for Batch Parallel Speculative Decoding PEARL : Parallel speculative decoding with adaptive draft length

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.746466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d6cfdfc-82f7-484e-b7f3-8669c44dbdaa · outbound

This paper cites TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput.

MineDraft: A Framework for Batch Parallel Speculative Decoding TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:48.916679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2db38151-d015-48e6-a8ae-808ede11aafc · outbound

This paper cites NVIDIA Nsight Systems 2024.2.

MineDraft: A Framework for Batch Parallel Speculative Decoding NVIDIA Nsight Systems 2024.2

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.052378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b58c61b5-a5b7-40b3-8993-285bbda241c0 · outbound

This paper cites Suffixdecoding: Extreme speculative decoding for emerging ai applications.

MineDraft: A Framework for Batch Parallel Speculative Decoding Suffixdecoding: Extreme speculative decoding for emerging ai applications

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.163280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dc45b6c-153e-401d-b5e2-27e2d4685cc8 · outbound

This paper cites Pytorch 2.7.0.

MineDraft: A Framework for Batch Parallel Speculative Decoding Pytorch 2.7.0

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.273155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e4581c2-f0a9-4a66-ac11-d89c5b5ce6e1 · outbound

This paper cites Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding.

MineDraft: A Framework for Batch Parallel Speculative Decoding Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.396548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf001af-1e76-4868-af25-779fd8ccd8a4 · outbound

This paper cites Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.

MineDraft: A Framework for Batch Parallel Speculative Decoding Outrageously large neural networks: The sparsely-gated mixture-of-experts layer

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.542832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40505f20-96ee-4095-9f69-9daaa04512a8 · outbound

This paper cites Distributed speculative inference ( DSI ): Speculation parallelism for provably faster lossless language model inference.

MineDraft: A Framework for Batch Parallel Speculative Decoding Distributed speculative inference ( DSI ): Speculation parallelism for provably faster lossless language model inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.663480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84c3e34a-924f-4d06-8687-964e55e632fb · outbound

This paper cites [performance]: vllm eagle performance is worse than expected.

MineDraft: A Framework for Batch Parallel Speculative Decoding [performance]: vllm eagle performance is worse than expected

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.791536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 525a5462-fea4-48d9-a2ae-a18be2bd0aa0 · outbound

This paper cites vllm v0.9.2.

MineDraft: A Framework for Batch Parallel Speculative Decoding vllm v0.9.2

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:49.904704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c4b610e-ef0b-44f1-9a79-82e169f1ce40 · outbound

This paper cites OPT -tree: Speculative decoding with adaptive draft tree structure.

MineDraft: A Framework for Batch Parallel Speculative Decoding OPT -tree: Speculative decoding with adaptive draft tree structure

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.122042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 495bec5c-218c-4941-a7c9-27b0094c92b0 · outbound

This paper cites Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution.

MineDraft: A Framework for Batch Parallel Speculative Decoding Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.222538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1460c91f-5374-4f7a-a1ba-68558e4f1b07 · outbound

This paper cites an unresolved cited work.

MineDraft: A Framework for Batch Parallel Speculative Decoding Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.340335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68231890-d1ee-4f21-be50-100e38d583e2 · outbound

This paper cites Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding.

MineDraft: A Framework for Batch Parallel Speculative Decoding Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.472687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4faeb111-b210-48ae-afd5-42d1a5d5ffcc · outbound

This paper cites ParallelSpec: Parallel Drafter for Efficient Speculative Decoding.

MineDraft: A Framework for Batch Parallel Speculative Decoding ParallelSpec: Parallel Drafter for Efficient Speculative Decoding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.581257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33fecf6e-5328-4b72-b60b-df007142ea84 · outbound

This paper cites Qwen3 Technical Report.

MineDraft: A Framework for Batch Parallel Speculative Decoding Qwen3 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.671835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c038e494-dc7d-4dab-a8b6-3e380776e45c · outbound

This paper cites Llm-tough-questions dataset: A collection of complex questions across 100 domains.

MineDraft: A Framework for Batch Parallel Speculative Decoding Llm-tough-questions dataset: A collection of complex questions across 100 domains

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.763821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 758d793c-0b58-4959-ae17-1fc0ca9dd364 · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding S., Kim, G.-W., Kim, S., and Chun, B.-G

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.839904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720e337c-508e-409e-bc07-bbbe1b19e5d4 · outbound

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

MineDraft: A Framework for Batch Parallel Speculative Decoding Draft & verify: Lossless large language model acceleration via self-speculative decoding

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:50.941081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0acec2aa-c140-4ca7-ba60-34a9ff906c32 · outbound

This paper cites E., and Stoica, I.

MineDraft: A Framework for Batch Parallel Speculative Decoding E., and Stoica, I

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:51.048500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.