Paper Citation Record · LEDGER

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs

As of 13 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2607.12550.

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

pith.paper-citation-record.v1
2607.12550 v2

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T06:31:53.101403Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

23 of 23 outbound references displayed

verified exact0
verified fuzzy0
unresolved22
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 827bd35c-0359-4c7e-80ba-a07f1d8cfe71 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:49.939253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2573aa-faa8-4189-b696-6d4092c86a7b · outbound

This paper cites Palu: Compressing KV-Cache with Low-Rank Projection.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Palu: Compressing KV-Cache with Low-Rank Projection

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:50.083575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2df317c-2521-41b6-87bb-340aba0b43c5 · outbound

This paper cites xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:50.156692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb8f0052-9b7c-40f8-9b59-6b92649e09eb · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:50.304516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73206696-185c-4131-b8c7-7be027366434 · outbound

This paper cites TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:50.527725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7bf9838-487d-4a90-94c9-c964ff8cd738 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:50.706165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2a7825-a097-4c57-aeaa-181ff0f096a0 · outbound

This paper cites Efficient streaming language models with attention sinks.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Efficient streaming language models with attention sinks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:50.940301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18798b0e-8c53-4ad9-a0cd-0eb8f4eef998 · outbound

This paper cites SnapKV: LLM knows what you are looking for before generation.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs SnapKV: LLM knows what you are looking for before generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.138797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b8950a-b9e7-4b69-bc4d-69c04ea48fc2 · outbound

This paper cites an unresolved cited work.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.349697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 944c61d5-35d4-4568-8d4e-c6009227592f · outbound

This paper cites A multilinear singular value decomposition.SIAM Journal on Matrix Analysis and Applications, 21(4):1253–1278, 2000.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs A multilinear singular value decomposition.SIAM Journal on Matrix Analysis and Applications, 21(4):1253–1278, 2000

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.484965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d956e8d-6dab-4c8f-984b-1aae4098a298 · outbound

This paper cites Kolda and Brett W.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Kolda and Brett W

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.557665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52379064-b7eb-4996-b959-ad598462874b · outbound

This paper cites Oseledets.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Oseledets

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.717283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2281b9bd-7911-40a9-9d17-a8b68de971a1 · outbound

This paper cites Kilmer and Carla D.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Kilmer and Carla D

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.818500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 638d9768-91c7-4658-b045-3989b8cb6824 · outbound

This paper cites Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, and James Hensman.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, and James Hensman

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:51.975637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d8f5f3f-7708-4fc1-9205-1979e106299e · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs SpinQuant: LLM quantization with learned rotations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.173019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49768a11-da60-4ada-a96e-81dea1c92c07 · outbound

This paper cites an unresolved cited work.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.294110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a70026f1-eeed-4157-b0f2-36ed9f759798 · outbound

This paper cites GQA: Training generalized multi-query transformer models from multi-head checkpoints.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs GQA: Training generalized multi-query transformer models from multi-head checkpoints

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.388501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d358eb6-cf24-4bb9-96a1-aacf303f8ca6 · outbound

This paper cites A new truncation strategy for the higher-order singular value decomposition.SIAM Journal on Scientific Computing, 34(2):A1027–A1052, 2012.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs A new truncation strategy for the higher-order singular value decomposition.SIAM Journal on Scientific Computing, 34(2):A1027–A1052, 2012

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.493157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbab4d25-8dd1-4dd3-85a7-4bdfbe399f2b · outbound

This paper cites Pointer Sentinel Mixture Models.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Pointer Sentinel Mixture Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.628467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26e3abdf-9b30-4085-98f6-8cc37d83b0fc · outbound

This paper cites an unresolved cited work.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.783401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e025c1ae-1194-4307-ac05-15808eeebbda · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Training Verifiers to Solve Math Word Problems

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.895441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04b699b-182d-4a01-b0ad-ce0cd22a6c4a · outbound

This paper cites Chi, Quoc V.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Chi, Quoc V

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T06:31:52.999268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a0fc7f-94c2-4126-9088-9d234fa13bf0 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 23

Resolution: malformed identifier; no resolver link, observed 2026-08-02T06:31:53.101403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.