Paper Citation Record · LEDGER

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

As of 5 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2607.28418.

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

pith.paper-citation-record.v1
2607.28418 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T08:00:58.889699Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

31 of 31 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14a5e14e-eb41-47ba-ba23-52a3b4de683e · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Check- points.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Check- points

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:55.639927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e3d8ed-21e3-46ad-a6e6-ef790d2c7e65 · outbound

This paper cites Aayush Gautam, Mukul Gagrani, Junyoung Park, Mingu Lee, Chiris Lott, and Narasimha Reddy.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Aayush Gautam, Mukul Gagrani, Junyoung Park, Mingu Lee, Chiris Lott, and Narasimha Reddy

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.693409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381875ad-a1bb-49c5-90f3-3719cf8d460a · outbound

This paper cites The Llama 3 Herd of Models.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.882801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e4d762-f8a0-43a9-91d1-7b22c387d452 · outbound

This paper cites Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.974233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b69cac-ce80-43e4-a590-29f0286678a3 · outbound

This paper cites What Matters in Transformers? Not All Attention is Needed.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning What Matters in Transformers? Not All Attention is Needed

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.075282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1549c1fe-7474-49c3-982e-86d91dba9b22 · outbound

This paper cites SkipOPU: An FPGA-based Overlay Processor for Large Language Models with Dynamically Allocated Computation.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning SkipOPU: An FPGA-based Overlay Processor for Large Language Models with Dynamically Allocated Computation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.151768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c213ac60-5bda-4ec8-91fd-8196332a3d9b · outbound

This paper cites Deterministic Differentiable Structured Pruning for Large Language Models.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Deterministic Differentiable Structured Pruning for Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.357203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 495e1156-fba4-46a6-b714-4b891f85dcdc · outbound

This paper cites Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.433405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7989027-7692-42dd-8eed-787777d7179d · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.514150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d3b58ca-6464-4a25-be78-e48ffc7d3e96 · outbound

This paper cites ISBN 979-8-89176-256-5.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning ISBN 979-8-89176-256-5

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.669892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5606eacd-749e-4cea-95ae-268e8308412e · outbound

This paper cites Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.743179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8917b35a-ef5c-47fd-b702-a68d36f06791 · outbound

This paper cites Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.954548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38989719-78ca-4c0e-b31c-7faf68d8168f · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Kimi K2.5: Visual Agentic Intelligence

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.029846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d115edfb-a0ad-44d3-b67d-fd5229029cd3 · outbound

This paper cites an unresolved cited work.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.163890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a565838b-d42b-4e62-9de7-fa3f45a0f6da · outbound

This paper cites ISBN 978-1-4503-6719-6.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning ISBN 978-1-4503-6719-6

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.302250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73e7ee6a-a361-482d-84aa-7685fb4d7dcb · outbound

This paper cites From data to model: A survey of the compression lifecycle in mllms.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning From data to model: A survey of the compression lifecycle in mllms

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.412700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f8c2fc2-b59f-4750-9b50-d251b67ba0b6 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.486093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc606566-4ed4-4758-9a86-1855bb5c6cdb · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning SGLang: Efficient Execution of Structured Language Model Programs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.573833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff557a35-e2cf-4d95-b30c-1011573e922a · outbound

This paper cites BlockPruner: Fine- grained Pruning for Large Language Models.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning BlockPruner: Fine- grained Pruning for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.648132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb712a9d-6a89-4271-91eb-9e7755f88ad2 · outbound

This paper cites mk,mnk->mn.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning mk,mnk->mn

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.715077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebed3562-4213-4a99-9420-a259a3cc4ef5 · outbound

This paper cites ,min(P−1, N K,g)−1do 6:PREFETCHK(g, q, qmodP, s (1),J)▷ ℓ= 1: predicated A loading 7:end for Group-local pipelined mainloop 8:fork c = 0,.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning ,min(P−1, N K,g)−1do 6:PREFETCHK(g, q, qmodP, s (1),J)▷ ℓ= 1: predicated A loading 7:end for Group-local pipelined mainloop 8:fork c = 0,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:58.805392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a16f832-abcd-4875-bdca-2421050f47ab · outbound

This paper cites an unresolved cited work.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Unresolved cited work

Reference 31

Resolution: malformed identifier; no resolver link, observed 2026-07-31T08:00:58.889699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bca8173-c57f-4dec-a62b-8923254aea64 · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.839457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b08da84-25c3-49ef-860a-93f29aa8e4cd · outbound

This paper cites CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.474852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc3e5f2-7465-4512-9f8b-73b9875790cd · outbound

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

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.297010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49fd00fc-d098-4dab-b424-1691a1e0d443 · outbound

This paper cites A VO: Agentic Variation Operators for Autonomous Evolutionary Search.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning A VO: Agentic Variation Operators for Autonomous Evolutionary Search

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:55.772555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eab88f6-d7a0-44b4-af9a-40fc86ba8dc1 · outbound

This paper cites Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.256732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f364ec6e-911e-4e10-99a4-791808beaefc · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:57.598751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cdcb772-d14a-47c6-aacd-83df05c840f4 · outbound

This paper cites ELANA: A Simple Energy and Latency Analyzer for LLMs.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning ELANA: A Simple Energy and Latency Analyzer for LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.072867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ccee6c-0cc0-4d8e-94a7-3c3a92efa665 · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:56.200139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b4fb0c-0755-4a82-bcac-3fcdb7c60651 · outbound

This paper cites A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations.

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-31T08:00:55.931442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.