Paper Citation Record · LEDGER

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2503.08879.

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

pith.paper-citation-record.v1
2503.08879 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:11:48.941234Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 04bf6933-e0ac-46ce-b63b-f50462c50b30 · inbound

SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators cites this paper.

SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:00:39.392292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 603475af-914f-474d-a411-ae9f945955aa · inbound

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 87

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:05:58.252809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4d07651c-4369-4567-b70a-ed50d58abea4 · inbound

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training cites this paper.

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 121

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T21:43:30.241418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5e428e53-99e1-4415-9363-72407946a81a · inbound

Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation cites this paper.

Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:11:12.549021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb7f7fc5-0671-4d8e-9eff-b6e8f15902a7 · inbound

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction cites this paper.

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T05:41:26.626805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f3425303-f25c-4e0a-b991-7560c2f8ba62 · inbound

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference cites this paper.

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:15:19.813677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4406306f-8c1a-40cb-8589-025a1708a645 · inbound

KVpop -- Key-Value Cache Compression with Predictive Online Pruning cites this paper.

KVpop -- Key-Value Cache Compression with Predictive Online Pruning LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T09:24:44.453258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe93245a-db3d-45e8-aaeb-9defb42edf5a · inbound

Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference cites this paper.

Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.797448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a029759-f192-4a38-914e-4db5cbbc1b11 · inbound

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs cites this paper.

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T13:43:53.889317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37373d5c-30a4-429b-82cb-e22d868e4768 · inbound

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs cites this paper.

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:11:48.941234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.