Paper Citation Record · LEDGER

xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 19 inbound Pith citation observations for arXiv:2503.18893.

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

pith.paper-citation-record.v1
2503.18893 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 19 of 19 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 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:44:35.753794Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T01:36:44.285178Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 2323e10e-2681-401c-858c-2587f9bb0dbb · inbound

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization cites this paper.

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T20:37:11.923378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec240f3a-ad6f-416e-a183-1e108f27f7a8 · inbound

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference cites this paper.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.405836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3012c4ce-845f-4f86-8624-3788abb276c6 · inbound

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents cites this paper.

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 466

Resolution: unresolved; no resolver link, observed 2026-08-03T05:54:01.125260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6d2683b-74f7-4df0-8bec-af1ed20f5162 · inbound

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents cites this paper.

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T05:54:01.193753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba6ebe7e-1688-4b82-a02c-389449dc5f23 · inbound

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction cites this paper.

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0c6b4727-c12e-4048-bee7-acd8f4a0bc8a · inbound

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation cites this paper.

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 55865eb6-1c62-44ec-a185-19dfd7c6da72 · inbound

SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference cites this paper.

SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 18a0dfb7-6c22-4aa4-a986-128f62934bf9 · inbound

eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization cites this paper.

eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c136ed24-8591-49dd-b7a3-8a79b3aedca4 · inbound

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast cites this paper.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2ec35399-e247-45bf-87cc-74ab27a3b098 · inbound

Compute Where it Counts: Self Optimizing Language Models cites this paper.

Compute Where it Counts: Self Optimizing Language Models xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 82c84bf0-82e1-44bc-8cc9-70ac19d372a5 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c00266c9-6829-445c-bd9c-7b8eaea65b94 · inbound

KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy cites this paper.

KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 808b7faa-baa7-4d25-923e-602faf626270 · inbound

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization cites this paper.

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6d7159a8-d923-4297-80c7-13120b7a0b7b · inbound

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference cites this paper.

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:03:59.868109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2cb6eef6-da4e-4ff3-ac06-09f6a9f5f949 · inbound

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents cites this paper.

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:36:44.286421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

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

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

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 28732b28-1bca-497d-b0b4-51481a81a173 · inbound

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse cites this paper.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T10:17:13.142422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f7401b1-e66e-4a35-82f9-b95cfafdcffa · inbound

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning cites this paper.

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:07:00.541065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7221584d-8357-49d7-8281-3bca7ca1802a · inbound

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry cites this paper.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.753794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.