Pith. sign in

Paper Citation Record · LEDGER

RAP: KV-Cache Compression via RoPE-Aligned Pruning

As of 9 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 1 inbound Pith citation observation for arXiv:2602.02599.

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

pith.paper-citation-record.v1
2602.02599 v4

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T06:17:13.042261Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T01:05:13.790381Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:59:57.348851Z

Reference resolution

17 of 17 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved15
  • parse uncertain0
  • malformed identifier2
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 619a5c6d-9ef0-4542-bc72-94aa3d7e43c5 · outbound

This paper cites GPT-4 Technical Report.

RAP: KV-Cache Compression via RoPE-Aligned Pruning GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:10.992317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:10.992317Z digest=sha256:e44f97449152cb3f888110d20f72ecd484b3d2b3f055135c071452b4b2424c68

Observation c59c549f-9ce0-4507-8ffa-ffbf7cfbbd95 · outbound

This paper cites Complete Experimental Results This appendix provides complete tables and supplementary plots for all experiments.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Complete Experimental Results This appendix provides complete tables and supplementary plots for all experiments

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.829264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.829264Z digest=sha256:22dd1e96473cc3c445a3a47b8611fd7d31e0542e3e49c3b6ef778a5a0156a5a9

Observation d43e52ac-0132-4936-8885-5cf052c05dd2 · outbound

This paper cites Longformer: The Long-Document Transformer.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Longformer: The Long-Document Transformer

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:11.275157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.275157Z digest=sha256:7a4c566480421c66987b40b24645ed9625a7d69e13e8e7c82b49d1f5da9d58e7

Observation 33776003-4509-4955-953e-d1b60e744463 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

RAP: KV-Cache Compression via RoPE-Aligned Pruning GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:11.401442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.401442Z digest=sha256:ae105129745cbc581d22f476fa8a68baacbebd06cabe690aa04909a1756a6fb4

Observation fb174046-ee9e-4bd0-9ec9-62349e5b80c7 · outbound

This paper cites Proof of Theorem 5.1 Proof.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Proof of Theorem 5.1 Proof

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.665509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.665509Z digest=sha256:5e3a25065ad808887e9761bf62bc0a3d76f2d9c28bdec286a817b63c02944c1f

Observation 7512a4fc-0fed-4163-815b-b5eae1ce4957 · outbound

This paper cites Ma, X., Fang, G., and Wang, X.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Ma, X., Fang, G., and Wang, X

Reference 7

Resolution
malformed identifier
no resolver link, observed 2026-08-04T06:17:11.795737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.795737Z digest=sha256:ed874d7c4ab224fbd03b3cd2c2c65004f258f05245122780bfbcf02f20efde1d

Observation af1ca3cb-fe79-4c0f-886a-c75eb6d193e5 · outbound

This paper cites Does quantization affect models’ perfor- mance on long-context tasks? In Christodoulopou- los, C., Chakraborty, T., Rose, C., and Peng, V.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Does quantization affect models’ perfor- mance on long-context tasks? In Christodoulopou- los, C., Chakraborty, T., Rose, C., and Peng, V

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:11.902985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.902985Z digest=sha256:d2801c2648f85022c9e84c3c6f940ac28acad736930d870b0eddd9a25c5d7c0d

Observation 2789b135-fab1-4917-b5e0-d49fb2d1b720 · outbound

This paper cites ISBN 979- 8-89176-332-6.

RAP: KV-Cache Compression via RoPE-Aligned Pruning ISBN 979- 8-89176-332-6

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.014905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.014905Z digest=sha256:3edbed12e66d8e93c1785e2a397cba88149e80df89947ce3a984460528cdefee

Observation 77dfa594-3baf-4fb0-a21d-29d786790e1c · outbound

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

RAP: KV-Cache Compression via RoPE-Aligned Pruning YaRN: Efficient Context Window Extension of Large Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.323290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.323290Z digest=sha256:2a118a187e5ad277593124db47cb1c9d81546842e63e87a09dd843fc44cbfae8

Observation 5bb88734-f62c-493e-aa6b-e1dcf3dfa57a · outbound

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

RAP: KV-Cache Compression via RoPE-Aligned Pruning LLaMA: Open and Efficient Foundation Language Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.484770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.484770Z digest=sha256:c2757b18e0e7a065f43cc59dc14b9f9df8af5bf5b512ea8adfae916e501eeb8d

Observation cbe1e3be-213c-4503-9e8f-eed5d032c06a · outbound

This paper cites an unresolved cited work.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Unresolved cited work

Reference 14

Resolution
malformed identifier
no resolver link, observed 2026-08-04T06:17:12.963873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.963873Z digest=sha256:311e4996b18d30047661981de25c9c3876064a711c5da28dd48ebd4e23ca94d2

Observation 843a6fe6-352b-45ff-babe-12bb18ef33f1 · outbound

This paper cites an unresolved cited work.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:13.042261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:13.042261Z digest=sha256:271d98e5d83f839ab887c0650936a530670faf01328c41a4bc91b0cf30eedce2

Observation 61077fed-6461-4d8d-a47e-92cba7005c6e · outbound

This paper cites emnlp-main.479/.

RAP: KV-Cache Compression via RoPE-Aligned Pruning emnlp-main.479/

Reference 479

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.150025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.150025Z digest=sha256:fb43c38b0a3e08e31d282f663449645dc729b018ea330d93995dbdc9a98d5b74

Observation 3fa80d22-adfc-48f5-88a0-06a3fa545159 · outbound

This paper cites Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:12.549851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:12.549851Z digest=sha256:cc15b7091b26a1f45560d76e2f4197c838a8d5556a4478a6a99222ed9aab4701

Observation e4ff99a5-de0c-49f5-802b-f81cb5d25b8e · outbound

This paper cites Qwen Technical Report.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Qwen Technical Report

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:11.134269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.134269Z digest=sha256:ee116d891a39cc157e560993077a70ee014d00b3e3f7f7052c597f228ae6d781

Observation 4f330ee4-6039-4bed-aaef-ba9672b6802f · outbound

This paper cites Distilling the Knowledge in a Neural Network.

RAP: KV-Cache Compression via RoPE-Aligned Pruning Distilling the Knowledge in a Neural Network

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:11.555167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.555167Z digest=sha256:1ae44a55cd70b14e801eba138e5762c9e55ab7102337224619557ed3c78f26d7

Observation 76414a5b-92eb-4d68-9bc3-599466e585fb · outbound

This paper cites DeepSeek-V3 Technical Report.

RAP: KV-Cache Compression via RoPE-Aligned Pruning DeepSeek-V3 Technical Report

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-04T06:17:11.657080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:17:11.657080Z digest=sha256:ff29e6d4e3f89be079855dc3be06369fc64596ccab17f5a07e00c8b489d6bacd

Pith citing papers

Observation 0f2f05ee-48c8-46e0-88d7-269fad521b26 · inbound

RoPE-Aware Bit Allocation for KV-Cache Quantization cites this paper.

RoPE-Aware Bit Allocation for KV-Cache Quantization RAP: KV-Cache Compression via RoPE-Aligned Pruning

Reference 40

Resolution
verified exact
arxiv_id, observed 2026-08-04T01:49:25.748849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-26T01:05:13.790381Z digest=sha256:3ad4ad04f4513da753ea284ffb2996145b664ce9fb6f80cfd0d1e030b0e5a159