Paper Citation Record · LEDGER

KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2508.04257.

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

pith.paper-citation-record.v1
2508.04257 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 6 of 6 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T17:04:24.573502Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T11:14:37.612699Z

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 f0444d80-a47e-4336-80b8-18b549fa9bb7 · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 286

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.782557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 941a7b1b-0002-4dab-a2d8-811c82e3db2e · inbound

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining cites this paper.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.756876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 27420f8b-2d0c-41f3-a13d-df94dd1219a3 · inbound

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models cites this paper.

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T23:23:26.812390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bf77deb5-b070-4ebe-9370-dace9342f59a · inbound

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models cites this paper.

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T17:04:24.573502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ade11d7c-0e74-4014-a1cb-322d12922c7a · inbound

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond cites this paper.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.564169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a921ef1b-1ac5-4a90-b9bc-1717c8e0e6a9 · inbound

Inference Time Optimization with Confidence Dynamics cites this paper.

Inference Time Optimization with Confidence Dynamics KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T11:14:37.614076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.