Paper Citation Record · LEDGER

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems

As of 15 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2607.24260.

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

pith.paper-citation-record.v1
2607.24260 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T19:52:42.384440Z

measured 26 of 26 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 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

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4f0ae3fc-641e-4237-8f66-2e15b7e33d97 · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.416031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34347e60-cbd2-40fc-8644-63b2e00726cf · outbound

This paper cites Yichao Fu, Peter Bailis, Ion Stoica, and Hao Zhang.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Yichao Fu, Peter Bailis, Ion Stoica, and Hao Zhang

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.492702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfb1070d-3e61-4d60-8d5d-1a763a6b9243 · outbound

This paper cites Break the Sequential Dependency of LLM Inference Using Lookahead Decoding.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.513351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f387e1f-e50b-47f9-88e7-abfa0bf8fff3 · outbound

This paper cites MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.866676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0fba4fa-d97a-4697-8d0d-772e88700e21 · outbound

This paper cites RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.036453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7ad40f3-f234-414a-9187-aa54b68363f6 · outbound

This paper cites HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.198924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82ca0f9-5e10-4282-8839-84d60ebae099 · outbound

This paper cites RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.311484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c3693d2-6bc8-4e24-bd51-c0a684580705 · outbound

This paper cites Yaniv Leviathan, Matan Kalman, and Yossi Matias.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Yaniv Leviathan, Matan Kalman, and Yossi Matias

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.581564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ec26a91-76f4-4783-adf2-ff458a971912 · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.696779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f74a3802-9cce-4e40-9636-bc42af1ea502 · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems SnapKV: LLM Knows What You are Looking for Before Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.850581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e18389ed-4d33-43e7-8afe-8a5b3dc9a772 · outbound

This paper cites Songshuo Lu, Hua Wang, Yutian Rong, Zhi Chen, and Yaohua Tang.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Songshuo Lu, Hua Wang, Yutian Rong, Zhi Chen, and Yaohua Tang

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.016565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62ef5918-1bb6-4586-933e-4da46e1d321c · outbound

This paper cites an unresolved cited work.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.120942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d5067ba-5810-409b-a479-a91571cfe6b7 · outbound

This paper cites 18 Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Anselm Levskaya, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems 18 Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Anselm Levskaya, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.272398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bcae3a8-d910-4835-b8d0-a087730dd323 · outbound

This paper cites Efficiently Scaling Transformer Inference.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Efficiently Scaling Transformer Inference

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.278984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3619d673-6479-49fb-9d44-0689df73651f · outbound

This paper cites Hanshi Sun, Zhuoming Chen, Xinyu Yang, Yuandong Tian, and Beidi Chen.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Hanshi Sun, Zhuoming Chen, Xinyu Yang, Yuandong Tian, and Beidi Chen

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.353442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50d6cf9-b693-4e7b-91d3-d5727e8a9b0a · outbound

This paper cites TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.358155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a525e8-1aba-45a8-af54-8183b70d9084 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.362436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5497a91d-d0c0-4572-ae55-5b44db2e9162 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Efficient Streaming Language Models with Attention Sinks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.366932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5bce959-286f-43d6-9b94-cf8c4e1fa9b2 · outbound

This paper cites CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.375553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c939d8-4bd1-4484-ab15-52c782c9758d · outbound

This paper cites H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.379821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f73a46d3-3366-4c66-a6c8-93850b5d0c9a · outbound

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

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems SGLang: Efficient Execution of Structured Language Model Programs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.384440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0325d77-2ceb-4a11-ad67-ed19ac16a81b · outbound

This paper cites Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:41.414223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a744c7-5f3e-4852-a7eb-545009321d18 · outbound

This paper cites Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.623478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843ab9aa-e843-44b6-93ca-3270e81d077d · outbound

This paper cites Neutrino Production via $e^-e^+$ Collision at $Z$-boson Peak.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Neutrino Production via $e^-e^+$ Collision at $Z$-boson Peak

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.082832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e223952-5305-451c-8b88-2c7a710f2c02 · outbound

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

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Accelerating Large Language Model Decoding with Speculative Sampling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.288142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0456cfa6-5983-491f-a644-272d4674dd63 · outbound

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

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:40.163554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.