Paper Citation Record · LEDGER

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets

As of 18 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2606.23961.

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

pith.paper-citation-record.v1
2606.23961 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T08:46:54.468405Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:23:36.514392Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

26 of 26 outbound references displayed

verified exact3
verified fuzzy0
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14f4af51-fbc0-4619-a47d-40a3aa01688a · outbound

This paper cites Claude Sonnet 4.5.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Claude Sonnet 4.5

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f866a02-c032-4da0-b804-67b3a3cc74fd · outbound

This paper cites LongBench: A bilingual, multitask benchmark for long context understanding.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets LongBench: A bilingual, multitask benchmark for long context understanding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb910308-4534-4866-b86f-6f880868121c · outbound

This paper cites PyramidKV: Dynamic KV cache compression based on pyramidal information funneling.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets PyramidKV: Dynamic KV cache compression based on pyramidal information funneling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1b5aaa-3ad1-489a-817e-0be4e3914b77 · outbound

This paper cites an unresolved cited work.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff78141-d599-4cbc-b2a6-56b67b48b03f · outbound

This paper cites FlashAttention-2: Faster attention with better parallelism and work partitioning.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets FlashAttention-2: Faster attention with better parallelism and work partitioning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e5d9b29-0cb5-4909-b0d3-6b4a9a6928b5 · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 270e8398-6542-4080-852a-594cf9d43a4b · outbound

This paper cites Efraimidis and Paul G.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Efraimidis and Paul G

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b22c1c-1cd1-4a83-b0de-da0241876b8b · outbound

This paper cites Kevin Zhou.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Kevin Zhou

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d3841e7-b6eb-455b-b427-480326f72a1f · outbound

This paper cites Dialogue without limits: Constant-sized KV caches for extended responses in LLMs.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Dialogue without limits: Constant-sized KV caches for extended responses in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 806498a7-8351-428f-bba3-b80d03b91ace · outbound

This paper cites RULER: What’s the real context size of your long-context language models? InConference on Language Modeling (COLM), 2024.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets RULER: What’s the real context size of your long-context language models? InConference on Language Modeling (COLM), 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c16fafe0-e8b7-4cc4-820f-9e7166e3d187 · outbound

This paper cites R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:29:45.342979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63fccb74-064f-4e3a-9d8b-6cc55d34703b · outbound

This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af07667e-47b5-4265-84e4-d9c415ff1708 · outbound

This paper cites SOCKET: SOft Collision Kernel EsTimator for Sparse Attention.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets SOCKET: SOft Collision Kernel EsTimator for Sparse Attention

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-04T10:29:45.346318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a8f21831-4ed9-4078-af48-7ce5cec0b282 · outbound

This paper cites Scout before you attend: Sketch-and-walk sparse attention for efficient llm inference.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Scout before you attend: Sketch-and-walk sparse attention for efficient llm inference

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:29:45.337347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 026314bf-9922-4a4e-8e66-2f0ebb262716 · outbound

This paper cites FAFO: Lossy KV cache compression for lossless inference acceleration via draftless fumble decoding.OpenReview preprint, 2026.https://openreview.net/forum? id=oSk9tP5Mgs.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets FAFO: Lossy KV cache compression for lossless inference acceleration via draftless fumble decoding.OpenReview preprint, 2026.https://openreview.net/forum? id=oSk9tP5Mgs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66c88e57-b50d-4f34-93c2-bfddd00c379e · outbound

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

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets SnapKV: LLM knows what you are looking for before generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6887c59c-7c91-4f0d-8082-d1cbf92f4348 · outbound

This paper cites DeepSWE: Training a fully open-sourced, state-of-the-art coding agent by scaling rl.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets DeepSWE: Training a fully open-sourced, state-of-the-art coding agent by scaling rl

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0310724-45e5-42c1-9352-3cf750cae582 · outbound

This paper cites OpenAI o1 system card.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets OpenAI o1 system card

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ade700f-2470-4e0c-ae71-1fed3f90e1b9 · outbound

This paper cites Efficiently scaling transformer inference.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Efficiently scaling transformer inference

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c91f76bd-bb46-4c04-9477-343c0141f1db · outbound

This paper cites Quest: Query-aware sparsity for efficient long-context LLM inference.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Quest: Query-aware sparsity for efficient long-context LLM inference

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8faacf8-55ec-4793-957e-369279269fa5 · outbound

This paper cites an unresolved cited work.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36b5a872-2eb3-4c32-93ae-d7aa7084313f · outbound

This paper cites Efficient streaming language models with attention sinks.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets Efficient streaming language models with attention sinks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d6e4f4c-6883-4b7c-956b-13899ede2983 · outbound

This paper cites KV cache compression, but what must we give in return? A comprehensive benchmark of long context capable approaches.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets KV cache compression, but what must we give in return? A comprehensive benchmark of long context capable approaches

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0543cf73-f419-4f52-82ca-3bdfbcbc5047 · outbound

This paper cites BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T10:29:45.333942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2e501005-158c-4919-855a-8411ba80e0b7 · outbound

This paper cites H2O: Heavy-hitter oracle for efficient generative inference of large language models.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets H2O: Heavy-hitter oracle for efficient generative inference of large language models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-26T08:46:54.468405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a08bd626-a5d0-4f1e-899c-7a1011f7ad24 · outbound

This paper cites how much can we shrink the cache before accuracy breaks?.

Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets how much can we shrink the cache before accuracy breaks?

Reference 26

Resolution: malformed identifier; arxiv_id, observed 2026-07-04T10:29:45.340157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation f1105785-c446-4a0b-bf84-5cc3136e7967 · inbound

Error Certificates for KV-Cache Eviction via Randomized Design cites this paper.

Error Certificates for KV-Cache Eviction via Randomized Design Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T07:23:36.514392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.