Paper Citation Record · LEDGER

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

As of 22 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2606.24467.

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

pith.paper-citation-record.v1
2606.24467 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T00:11:57.763089Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T12:56:45.291959Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact12
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ed88dafd-6b39-4038-90b5-adccec79cdad · outbound

This paper cites GPT-4 Technical Report.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:49:58.020178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1da52462-0a7a-4175-a718-a484a8f40fc7 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 161d8000-00ce-4020-bce7-9a781805fa75 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082c550d-f1f2-4e4b-9086-4876c57c6822 · outbound

This paper cites The Llama 3 Herd of Models.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference The Llama 3 Herd of Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:49:58.017771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ba327b48-32b6-4ba4-a725-b7086922418b · outbound

This paper cites Qwen2.5 Technical Report.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Qwen2.5 Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:49:58.044274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 840454fa-54ab-4dfd-8a6c-e695e68eabcb · outbound

This paper cites Wang, Y.-G.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Wang, Y.-G

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db03baaf-a8e7-4ab6-ad70-a8f34aa04018 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95bb6d88-1f3e-47bd-8e44-4d6174afc6c8 · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.047166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 176e4426-a23b-4b4d-96b4-7f985a40e75f · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45f06e1-7dfe-43e0-bd94-2fe77032d648 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59c55722-3d3e-4f8b-b4c8-15fa7c2c5b6e · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57f7f1be-1426-4318-968a-5fbbcaeee64d · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a59fb7dd-2e04-460d-8b4d-4e58d22fb382 · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:49:58.037140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b0c13995-5a76-4ded-9274-2fb9a43db4c8 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae98eed7-e0a9-484e-b8d9-a1fe2adcd90c · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4aec25-f8a9-4260-be27-fa2d8910f6e0 · outbound

This paper cites Ainslie, J.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Ainslie, J

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca51b5c-94c1-4a51-bab3-4691d41f8f00 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f0c9e18-9979-4692-9235-4dffb5f47504 · outbound

This paper cites Not all heads matter: A head-level KV cache compression method with integrated retrieval and reasoning.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Not all heads matter: A head-level KV cache compression method with integrated retrieval and reasoning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.042075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cdcca5e3-b201-4475-84b2-8babd76b69a8 · outbound

This paper cites Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:49:58.039510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2d926237-75ef-4cc0-9cd3-eaec92c1b960 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d5d0be6-e42c-4357-9e61-444de75be77d · outbound

This paper cites Zhang, Y.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Zhang, Y

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33567cdf-0ff6-4191-9970-d799ef3abda9 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81338119-39bd-47fc-b16b-1fce231afc7f · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13e049c5-6e4f-4053-8fa5-69be06fac3b9 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e356cb-8a28-4b84-8ee9-47151dc07cd3 · outbound

This paper cites In-context Learning and Induction Heads.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference In-context Learning and Induction Heads

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:49:58.031461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7c08a395-bf1a-49ed-838e-735220d663a0 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc7873b9-9a69-4ffb-8bf2-7ca248dcc20f · outbound

This paper cites Attention Heads of Large Language Models: A Survey.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Attention Heads of Large Language Models: A Survey

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.033929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a08b16b2-a9a9-4867-a995-00fcfbe4a800 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8729ed96-5f0a-4d9b-a027-454555b9498e · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3443cbb6-d9b8-46e5-923a-70d22af1dae9 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9276c2-1721-4d88-bea3-3c653ebbe4fe · outbound

This paper cites Which Attention Heads Matter for In-Context Learning?.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Which Attention Heads Matter for In-Context Learning?

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.030660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation da331ebc-b840-425a-af55-3348867563e3 · outbound

This paper cites RazorAttention: Efficient KV Cache Compression Through Retrieval Heads.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.028076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a31b896d-ed4e-4428-8bb3-3714b9e5800b · outbound

This paper cites From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.026479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 83395ff6-9e1a-478e-ad13-8686005f2d84 · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18816ac6-2b77-4c89-9f59-bcd679dc6ff6 · outbound

This paper cites Kamradt, Needleinahaystack, https://github.com/gkamradt/LLMTest_NeedleInAHaystack, 2023.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Kamradt, Needleinahaystack, https://github.com/gkamradt/LLMTest_NeedleInAHaystack, 2023

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5787d02d-c279-4a55-9d16-fb257ad763a3 · outbound

This paper cites Dao, Flashattention-2: Faster attention with better parallelism and work partitioning, in: The Twelfth International Conference on Learning Representations, 2024.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Dao, Flashattention-2: Faster attention with better parallelism and work partitioning, in: The Twelfth International Conference on Learning Representations, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f655f36-06c5-4b15-895a-e09ed15f658f · outbound

This paper cites Jiang, Y.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Jiang, Y

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38333a1e-4bf2-4285-8410-eb6961e9fada · outbound

This paper cites an unresolved cited work.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-26T00:11:57.763089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 22bdc162-20b6-4d40-8af9-6cef3be9f150 · inbound

Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory cites this paper.

Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T12:56:45.291959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.