Paper Citation Record · LEDGER

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers

As of 21 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2507.06517.

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

pith.paper-citation-record.v1
2507.06517 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:10:01.390805Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

38 of 38 outbound references displayed

verified exact2
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f23e687-b51d-4007-9a7d-c401816796f0 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.141523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd74c056-2c14-4c44-8a9b-ab95831d2caf · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.149847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2058252-854e-40fc-83a4-e0e736a0a99c · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.159355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 909506b7-faec-4605-9ec8-43fbedf0c25a · outbound

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

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.168058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0948fccb-6ff9-4cde-894b-3291a937a64e · outbound

This paper cites The Llama 3 Herd of Models.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers The Llama 3 Herd of Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.174335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18d9c572-7fdc-4e8b-bcc0-0d3fa60daa9b · outbound

This paper cites ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.179964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f927478e-2834-44c1-a324-84b6c04986a9 · outbound

This paper cites Mistral 7B.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Mistral 7B

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.187348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a09754-ce12-4f78-a4eb-768cfbd703a5 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.195409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfa7e96e-266d-4d86-a1be-924418abc8ab · outbound

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

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers SnapKV: LLM Knows What You are Looking for Before Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.203208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 338b3950-8251-4c0f-99be-28abbd3377f5 · outbound

This paper cites MiniCache: KV Cache Compression in Depth Dimension for Large Language Models.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.211946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fdba2e3-31ff-42f0-8175-5110e941edf5 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:10:02.958339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c95eb433-c79e-41b0-ad08-0d5889a4ebb0 · outbound

This paper cites Model Hemorrhage and the Robustness Limits of Large Language Models.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Model Hemorrhage and the Robustness Limits of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.234102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6de484d-3952-42d4-bd55-90adf7f0a6a8 · outbound

This paper cites GPT-4 Technical Report.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers GPT-4 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.240080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cedb03dc-0ed5-417f-b6fe-93a3f06cca24 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Code Llama: Open Foundation Models for Code

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.245546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d68095d-1839-48b6-bb9b-f6b7f9013ff1 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Fast Transformer Decoding: One Write-Head is All You Need

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.252625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66924c83-215c-41d0-b708-5ffa2f2154c6 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:10:02.815580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3052772c-d3e2-4298-a07d-dbd0d9d2fce4 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:10:02.657536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 34f513a7-45ee-4117-9607-8b2ff82b929e · outbound

This paper cites Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.272177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a16d05fe-7f1f-41ff-bfe8-b04508726fb9 · outbound

This paper cites AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.279099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5583f0b-12c2-4186-8b24-9606c559e13f · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.285988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7596169-23e7-4742-955b-2e4a21a5c4fa · outbound

This paper cites D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.293262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd288fb9-7a4b-4fb8-b39a-a5dab284f6bb · outbound

This paper cites Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.298502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12ddd718-c7ce-4e1d-aa7f-fba1157d9910 · outbound

This paper cites Chi, Quoc V.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Chi, Quoc V

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.304251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 598a83f7-34fb-43d5-9443-2987dcd35c1d · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.311005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac18d532-b1fb-41e0-bca9-3365bec40329 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.316923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62fb2d66-e718-45ca-931f-b3977f2d1a89 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.321670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc068d4b-028d-4e40-aeb8-fa23a8cb2e7f · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.327165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b232ec-8ee1-41d4-bc37-ec79c6e23609 · outbound

This paper cites No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.332282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b3b2c85-1c67-4692-8799-445c095d568e · outbound

This paper cites BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.337858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07873f95-ec27-4261-9456-7458ae1c2872 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 30

Resolution: verified exact; doi, observed 2026-08-06T19:10:01.502841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c0dc3682-d4ee-42ea-bc80-c6e869a2ab90 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.347645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27186367-5797-4737-961a-b045ba22433b · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 32

Resolution: verified exact; doi, observed 2026-08-06T19:10:01.461578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a4760a97-6ed4-440c-a581-008cf9b4c222 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.359336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881219f6-dd4c-46bd-bba7-279f8ef78d02 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers OPT: Open Pre-trained Transformer Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.365544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fb9500a-4b9b-43bd-b9e4-c8d4a40a5711 · outbound

This paper cites an unresolved cited work.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:10:02.464695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2a58ea80-198c-4d79-91a5-87f34443b4d2 · outbound

This paper cites Barrett, Zhangyang Wang, and Beidi Chen.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers Barrett, Zhangyang Wang, and Beidi Chen

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.377937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17425d81-1528-4a3d-b696-ece85a124c6f · outbound

This paper cites online" 'onlinestring :=.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers online" 'onlinestring :=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.384792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ec6cba-9c59-477b-9854-08077b409f24 · outbound

This paper cites write newline.

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers write newline

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:01.390805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.