Pith. sign in

Paper Citation Record · LEDGER

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty

As of 19 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 1 inbound Pith citation observation for arXiv:2412.09036.

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

pith.paper-citation-record.v1
2412.09036 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T17:24:49.287823Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T11:52:50.864071Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T11:54:38.180786Z

Reference resolution

32 of 32 outbound references displayed

  • verified exact3
  • verified fuzzy0
  • unresolved29
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2139d400-8777-462d-84ce-dec67c0f0c62 · outbound

This paper cites online" 'onlinestring :=.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty online" 'onlinestring :=

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.079941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.079941Z digest=sha256:d2d92630b3cd6bac50ba07dc9ac5a868d336ed830f45895a45a31019cb6bbbef

Observation 64629250-c34f-46e5-a19c-b802fef36bf1 · outbound

This paper cites write newline.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty write newline

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.086902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.086902Z digest=sha256:928b4f56b235654101f04b90216871ae359532be060447d8e5195b1a966fb90d

Observation a942ae48-2e62-47f6-9569-9b123b97590d · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.092661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.092661Z digest=sha256:359d6bdec977dd4042cf12582401cfa0d6404e4fd9723c7ef7ea1e714b008e78

Observation 8f907e0f-a75f-4b1e-ad26-5c8ad6618584 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.099952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.099952Z digest=sha256:1e530d7324f2bf3b26c29cc8f99fb95fd6beeed64b501334c36f520af69618cf

Observation 60b0bda1-d7c9-4bef-8e28-4396cea8b2fc · outbound

This paper cites NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.107528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.107528Z digest=sha256:664facb83df6fc11dd68ad2e200a47ef13857d4b6fc18d98343ac2f164ca2145

Observation a37e6779-8c13-4269-a806-659cea4bf687 · outbound

This paper cites The Llama 3 Herd of Models.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty The Llama 3 Herd of Models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.114516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.114516Z digest=sha256:580fe99394374b69fc972756260fb17b9bc51e3f59f73b82f6bb6e619530e9fa

Observation f942760e-8937-462a-aa72-b8b2b9395f4c · outbound

This paper cites Data Engineering for Scaling Language Models to 128K Context.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Data Engineering for Scaling Language Models to 128K Context

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.121564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.121564Z digest=sha256:6513bb08a3d914e07dec8cbdcb8dfbf2714f332ab40ff0c91660815960519547

Observation 6e9049fc-89a5-4b22-9ca2-0634cecd38d2 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.127394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.127394Z digest=sha256:adb1521cf45faf67dd6bcb409b142137f3a608c3f22aa2c118500c68c1905585

Observation 4032495a-d41e-40fa-8ed8-dc4e247d2b74 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.133100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.133100Z digest=sha256:ab133edefcbc6373ec02d1217d3d3340ad36a0dd641f71a70d73ed57b1802f06

Observation b403d45f-3e4b-4c78-ace3-630e1fc6259d · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-11T17:24:49.923286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-11T17:24:49.138758Z digest=sha256:259140864dad1382136d15c88b92383fc9983a2624d10a4da12494fa11beb154

Observation 35ea4666-d9fb-4252-a204-b945015cd709 · outbound

This paper cites Mistral 7B.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Mistral 7B

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.144176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.144176Z digest=sha256:5ea20743d71916462b97ce3af6cd32299af349e185da011eb021061e992addf0

Observation d9cb68cd-d816-463d-94c5-f34412ac5db7 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.151319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.151319Z digest=sha256:008f62e3c505e261cf2d26eeda04e4b9a9e978ad1a9f092a0d8f75b2ee6283c4

Observation 8715b043-ef25-44ab-9e50-660139472b24 · outbound

This paper cites Evaluating Open-Domain Question Answering in the Era of Large Language Models.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Evaluating Open-Domain Question Answering in the Era of Large Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.158073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.158073Z digest=sha256:33e75251d7bae78d99a2b8d401327c232dc98eadcfb6dc0cb186e51ac23ae2f7

Observation df526e38-6a9c-4df5-be57-f02343926d1d · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.163973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.163973Z digest=sha256:805ad27d95fd919c1d39f8ad58a15e396df9c428a9ae5ba870d39caf264ecdb2

Observation cf54ed05-5ca7-42ff-8187-ccf3ddf75f0e · outbound

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

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty SnapKV: LLM Knows What You are Looking for Before Generation

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.169759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.169759Z digest=sha256:9ac8263f1f5763afe556e3b0203767b3e40d2b4be00792a8dcb91a5515467e17

Observation 4c8f547a-9526-4bb9-8fa2-224cf23e22e6 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.176070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.176070Z digest=sha256:8e0983002fee30b1233c9b441fb89563f23c765d4543863a898615ef466ab3cb

Observation 48440ad3-d34c-46ea-9f53-be55688a34a4 · outbound

This paper cites Transformers are Multi-State RNNs.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Transformers are Multi-State RNNs

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.181367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.181367Z digest=sha256:9a492b71bcba60f3569bf00732b4f09f1594afb05e074b5a7e84a8560a894a61

Observation 75abbe0b-4149-42b5-9a08-bc0b60f1a85f · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-11T17:24:49.867136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-11T17:24:49.194775Z digest=sha256:05a7439994c2483519f653f4b34f096af8747bd8f50cdff335230743dbbf01cd

Observation 979f8fda-5550-47b0-a914-dbb45ad4bdfe · outbound

This paper cites YaRN: Efficient Context Window Extension of Large Language Models.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty YaRN: Efficient Context Window Extension of Large Language Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.199935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.199935Z digest=sha256:ede5177086e3c1898ea17c9be28f93eec3644ef3b7c5e9a63e3e0da4f500931d

Observation c30e8d39-45b7-469f-8bfc-418838e6a521 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.206283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.206283Z digest=sha256:15ba0771b214e195ae3d97a311cb5654ec6b624da7e7010faa968cd9baa994cb

Observation 44e8655f-d43e-475f-9e8f-a1ed7056542a · outbound

This paper cites On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.212636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.212636Z digest=sha256:9887a42bcf85580800869b527774d96bc9dddf806735e412ffca160d1dad940f

Observation df2f3ff9-690c-4e84-97cb-72f5b7e8580e · outbound

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

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Code Llama: Open Foundation Models for Code

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.220192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.220192Z digest=sha256:db0ac2644588c40139b54da18a4baf1c1110f680bc6bb3677fcfa17fe7033deb

Observation e41d61fc-6220-4f4c-8ca8-7db474b0c7d1 · outbound

This paper cites an unresolved cited work.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Unresolved cited work

Reference 23

Resolution
verified exact
doi, observed 2026-08-11T17:24:49.341179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-11T17:24:49.226531Z digest=sha256:e5a11729bc2330ff3c83e96c31cb0f094c7791293171b27cc01c7c540af87376

Observation 9d6fbba5-039a-49ab-95f6-70facf1e504f · outbound

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

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.236157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.236157Z digest=sha256:8fd89106f152f0b48f16ac3844d9c547a3dea8a9f60f6e17fc636dc47b6c69bb

Observation a4044e53-363f-4277-afb6-33742ffc2aa0 · outbound

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

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.242538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.242538Z digest=sha256:539280c562b3892c12712b1f16cfb76a81b424be10cd92239b13262247c8f5bb

Observation 657f434f-fa19-4a4a-9167-460d07159946 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Efficient Streaming Language Models with Attention Sinks

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.250180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.250180Z digest=sha256:b8db0c656d1187863d27fc748c93e54ce24fbcf11b93cb81cc83da9012f66ad1

Observation 06d812ad-d052-4c96-b8a5-43a226a96667 · outbound

This paper cites PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.256708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.256708Z digest=sha256:e449874196b5b7c2c60e4b64a550dcdc9b6b9060805d4c916b79ac54377044c5

Observation 9d6e2fbc-997c-442b-ad14-ae3ae3290323 · outbound

This paper cites Towards the Law of Capacity Gap in Distilling Language Models.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Towards the Law of Capacity Gap in Distilling Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.263328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.263328Z digest=sha256:a1a926b638117d6f3e3908c9d1bb3c118f39c4d97797c8898d18b803d08bad21

Observation edbf15ad-5a95-485b-baa2-0952f1dd7b91 · outbound

This paper cites MoDification: Mixture of Depths Made Easy.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty MoDification: Mixture of Depths Made Easy

Reference 29

Resolution
verified exact
local_arxiv, observed 2026-08-11T17:24:49.475304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-11T17:24:49.268837Z digest=sha256:c335a54286bc0b3eadb0a9dff812f889bdd0b3e8e6b64a042511ed128f7332f9

Observation 6800664b-bbb6-4378-9703-5c7722aededd · outbound

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

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.275814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.275814Z digest=sha256:3be1f1bdacfe1bc8330d386a32c1a70fc7275e836621fe60d957fa9170e7eb71

Observation 43eb817a-82b2-4646-8d44-e6e34f50bd2d · outbound

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

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-11T17:24:49.281357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T17:24:49.281357Z digest=sha256:312a84906f735afc4add15fbe44fa767d64ee624e369e9dcfaeb7441d2ce8e33

Observation c9d67560-3947-47c6-b429-f1d1a2aebe8d · outbound

This paper cites Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective.

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective

Reference 32

Resolution
verified exact
local_arxiv, observed 2026-08-11T17:24:49.401673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-11T17:24:49.287823Z digest=sha256:55a1c999c3449600c06a43a5e03fe475655cd00f975f647836dcf69106235939

Pith citing papers

Observation fd1b4ba8-56e7-44b9-ad00-d1000099beb8 · inbound

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM cites this paper.

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty

Reference 27

Resolution
malformed identifier
arxiv_id, observed 2026-06-30T11:54:38.182377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-30T11:52:50.864071Z digest=sha256:26272d7666b3d38e9eb624c014094c6d772e0eb7505a3248e337f7302ed8fe3c