Paper Citation Record · LEDGER

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference

As of 6 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2605.18071.

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

pith.paper-citation-record.v1
2605.18071 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T11:13:46.098095Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

43 of 43 outbound references displayed

verified exact11
verified fuzzy1
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 58af20b4-3e62-4673-beee-6e3050b6c43c · outbound

This paper cites Phi-4 Technical Report.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Phi-4 Technical Report

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T11:18:13.970234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a19fa9c7-1630-4fbc-ad70-37f119a3e787 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.110581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 78744fdf-3bf6-442c-ab96-72c14032bd2b · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.101618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ecadf9d-71e6-475e-807a-71bf162a3517 · outbound

This paper cites Gonzalez, Matei Zaharia, and Ion Stoica.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Gonzalez, Matei Zaharia, and Ion Stoica

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T11:23:27.103683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 92fa7ed9-3a23-4685-83a5-b3c89c212da5 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.070913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4c4fda79-6e3a-4808-b4df-5009f6b263fe · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.105671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f2f9e22f-e5e3-41d8-8e85-0a0a92d729d2 · outbound

This paper cites RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T11:18:13.973417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7b9cfec4-5556-45cc-95c1-f586413ad10a · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.067462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a948e925-27a9-457f-bb01-3e95978464f6 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.107251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae3c957c-1368-4785-986e-ec521f5483c0 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.093309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 12b2ecfb-9372-4308-aba6-e19cbcbdb921 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.094995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f9d250e7-9d73-444c-8ea4-c857ef8a6d0a · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.098095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34d5394c-d272-400d-94a5-10bd33560629 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.091574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 409149ed-558e-4484-ab82-f429ff0bfb4f · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.086215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 353c9f33-5c95-42e1-80e4-6fc6c175c860 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.088048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7106f95e-7c76-401c-88d2-60c95ed8228c · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.064112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 293b47d1-f7ba-406a-8b2c-32a14ab4a1e6 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.065755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9df60470-ba16-4bd9-9fa3-769b49d555f1 · outbound

This paper cites FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:18:13.988453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8d5d52d0-9a42-40bd-a472-34ceed96f5dd · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.069260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 105becf6-d1c0-45e2-96a0-b07b899bedd5 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.072741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 085003e4-696a-4ef7-87b3-c39a1326c600 · outbound

This paper cites RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.967617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6b611d15-8b8a-49ce-beb9-38753f083462 · outbound

This paper cites CoRR , volume =.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference CoRR , volume =

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:18:13.982324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8d377bdb-ab8e-4879-bd48-443a7f4da7bb · outbound

This paper cites MoBA: Mixture of Block Attention for Long-Context LLMs.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference MoBA: Mixture of Block Attention for Long-Context LLMs

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.985129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 37443076-863c-4fbb-9848-0594ead56c4c · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.076137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aa46d22f-8665-4d0d-b47c-5115b8ab97cb · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.062422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3ec8f4d3-fffc-4fb5-b8dc-ce02a4f3262f · outbound

This paper cites GPT-4 Technical Report.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference GPT-4 Technical Report

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.979080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 28f35947-156c-43f2-b3b2-584b3297c7b5 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.058737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8fdbb942-6f16-489d-9479-6c6919d676e8 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.060763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b5c17c63-cb96-43ac-b79c-6711c463966c · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.077904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b4e0a082-1ec4-43dc-83a5-cb406ee1b410 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.089838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 18e0dc24-3204-4fee-991b-4698e8cc053a · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.099955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e10107a8-aaa8-43ad-8e0e-cdcc3a0c5feb · outbound

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

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference LLaMA: Open and Efficient Foundation Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.991247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4558a0a5-c168-49ac-888b-34d70ec86523 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.108756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c4e9f83a-6f42-4dae-9019-a22385b9ac07 · outbound

This paper cites Strata: Hierarchical Context Caching for Long Context Language Model Serving.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Strata: Hierarchical Context Caching for Long Context Language Model Serving

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:18:13.961843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 720b80ac-a6d2-4cf1-9c1e-e49c8cf1755e · outbound

This paper cites Qwen3 Technical Report.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Qwen3 Technical Report

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.956290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f7c9d456-837e-484c-8019-eb6747c3711a · outbound

This paper cites Qwen2.5-1M Technical Report.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Qwen2.5-1M Technical Report

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.976207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6d25ad3e-05ed-4fa5-9671-924a2237e6e7 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.074471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b76bfda8-a320-4a7d-90ac-c4b8e8ad7504 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:18:13.964774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eae2d01d-4cf6-447b-bf2b-9683bed1c0c8 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.084484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 56ffb6cc-95ab-4750-9db9-f26ba9e159a1 · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.082843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8246754b-f481-416b-9f79-16f07c5cff9c · outbound

This paper cites LLM Inference Unveiled: Survey and Roofline Model Insights.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference LLM Inference Unveiled: Survey and Roofline Model Insights

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:18:13.959019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 388c9f7a-9720-47dc-8801-28bd74ef6e2d · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.079492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cc9d6acd-82d4-4e80-adad-4a460ecced2a · outbound

This paper cites an unresolved cited work.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-05-20T11:23:27.081131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.