Paper Citation Record · LEDGER

Accurate KV Cache Quantization with Outlier Tokens Tracing

As of 19 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 5 inbound Pith citation observations for arXiv:2505.10938.

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

pith.paper-citation-record.v1
2505.10938 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:05:39.021493Z

measured 26 of 26 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 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:37:49.294686Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T04:15:19.933053Z

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy7
unresolved12
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c7394e10-f835-400d-be0c-3590a01d34e5 · outbound

This paper cites He would ask probing questions to expose the contradictions and inconsistencies in their arguments, and to lead them to a deeper understanding of their own beliefs.

Accurate KV Cache Quantization with Outlier Tokens Tracing He would ask probing questions to expose the contradictions and inconsistencies in their arguments, and to lead them to a deeper understanding of their own beliefs

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.376689Z

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 3576c5e7-8a53-45d9-a9a2-8ce2f2dd1e40 · outbound

This paper cites He would engage in conversations with others, using his questions and their responses to challenge their beliefs and to encourage them to think more deeply about their ideas.

Accurate KV Cache Quantization with Outlier Tokens Tracing He would engage in conversations with others, using his questions and their responses to challenge their beliefs and to encourage them to think more deeply about their ideas

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.361382Z

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 01d7d310-3c77-46dc-844f-423d2aefd6cc · outbound

This paper cites By using irony, he could expose the flaws in their arguments and lead them to see things from a different perspective.

Accurate KV Cache Quantization with Outlier Tokens Tracing By using irony, he could expose the flaws in their arguments and lead them to see things from a different perspective

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.345676Z

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 fe12acd6-ef3d-41fc-96c0-34736bfa7851 · outbound

This paper cites ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification.

Accurate KV Cache Quantization with Outlier Tokens Tracing ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.932062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 314a7d1b-a983-4a50-a744-b0f41a356f60 · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

Accurate KV Cache Quantization with Outlier Tokens Tracing GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.937281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d638b8-3d19-4c0b-8d80-5cd6cc42ea00 · outbound

This paper cites HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly.

Accurate KV Cache Quantization with Outlier Tokens Tracing HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.942898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 495ae6d9-1607-460f-b0a5-7b520f6ab9ba · outbound

This paper cites Effectively Compress KV Heads for LLM.

Accurate KV Cache Quantization with Outlier Tokens Tracing Effectively Compress KV Heads for LLM

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.948600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4db7d74b-4869-41f8-9d4b-458c8f612fc6 · outbound

This paper cites MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding.

Accurate KV Cache Quantization with Outlier Tokens Tracing MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.953553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ba209e7-59be-4271-b6f0-0875c9b3703f · outbound

This paper cites outlier channels.

Accurate KV Cache Quantization with Outlier Tokens Tracing outlier channels

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T21:05:39.251822Z

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 203b18a8-423a-43a5-be59-fb5002a0ef47 · outbound

This paper cites By presenting seemingly contradictory statements, he could encourage his interlocutors to think more critically about their beliefs and to question their assumptions.

Accurate KV Cache Quantization with Outlier Tokens Tracing By presenting seemingly contradictory statements, he could encourage his interlocutors to think more critically about their beliefs and to question their assumptions

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.330342Z

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 49c4a566-0023-422e-bfdf-fd38fda8850b · outbound

This paper cites He would use his questions and dialogue to help others discover new truths and to challenge their existing beliefs.

Accurate KV Cache Quantization with Outlier Tokens Tracing He would use his questions and dialogue to help others discover new truths and to challenge their existing beliefs

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.315110Z

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 77873b18-ea08-4b4d-bdc6-6827c981b55a · outbound

This paper cites By using comparisons and contrasts, he could help his interlocutors to see things from a different perspective and to develop a deeper understanding of the issues at hand.

Accurate KV Cache Quantization with Outlier Tokens Tracing By using comparisons and contrasts, he could help his interlocutors to see things from a different perspective and to develop a deeper understanding of the issues at hand

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.299944Z

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 0708e2f4-843f-4d30-b971-3e390e67c11a · outbound

This paper cites He would use his questions and dialogue to challenge the beliefs of others and to lead them to a deeper understanding of the issues at hand.

Accurate KV Cache Quantization with Outlier Tokens Tracing He would use his questions and dialogue to challenge the beliefs of others and to lead them to a deeper understanding of the issues at hand

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:39.284128Z

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 461dcdbe-cf7c-4a2b-87a6-ae5ee1c12e76 · outbound

This paper cites an unresolved cited work.

Accurate KV Cache Quantization with Outlier Tokens Tracing Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:39.267959Z

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 dbbd040f-fceb-4d2d-9c5a-3a6fa3524353 · outbound

This paper cites an unresolved cited work.

Accurate KV Cache Quantization with Outlier Tokens Tracing Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:39.236732Z

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 5c11b5b3-3bd8-42f0-a7df-b174fe3b621d · outbound

This paper cites an unresolved cited work.

Accurate KV Cache Quantization with Outlier Tokens Tracing Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:39.221165Z

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 0f659b60-065f-450b-92b4-00450319ac18 · outbound

This paper cites an unresolved cited work.

Accurate KV Cache Quantization with Outlier Tokens Tracing Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:39.203698Z

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 1735ed3d-e85a-47c8-bc04-235f23e03946 · outbound

This paper cites The retained out- lier tokens are excluded from quantization and stored in full precision.

Accurate KV Cache Quantization with Outlier Tokens Tracing The retained out- lier tokens are excluded from quantization and stored in full precision

Reference 21

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T21:05:39.186827Z

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 ca0ae5aa-a852-48da-916d-23e41d771adb · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Accurate KV Cache Quantization with Outlier Tokens Tracing Training Verifiers to Solve Math Word Problems

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.921403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d503877-b687-480c-bdd7-756c1e8267bf · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

Accurate KV Cache Quantization with Outlier Tokens Tracing QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.915221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb3cd3e-b424-4498-a42e-5d81ea0f25b4 · outbound

This paper cites QAQ: Quality Adaptive Quantization for LLM KV Cache.

Accurate KV Cache Quantization with Outlier Tokens Tracing QAQ: Quality Adaptive Quantization for LLM KV Cache

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.926542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 3a847e47-32ef-4eb2-875a-e477e207f27b · inbound

Survey of Specialized Large Language Model cites this paper.

Survey of Specialized Large Language Model Accurate KV Cache Quantization with Outlier Tokens Tracing

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:49.294686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02953de0-26de-4c2d-961f-45d70da22f35 · inbound

Harmonia: Algorithm-Hardware Co-Design for Memory- and Compute-Efficient BFP-based LLM Inference cites this paper.

Harmonia: Algorithm-Hardware Co-Design for Memory- and Compute-Efficient BFP-based LLM Inference Accurate KV Cache Quantization with Outlier Tokens Tracing

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T04:37:29.127791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6355de-d820-4001-9fed-72a72dff856f · inbound

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation cites this paper.

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation Accurate KV Cache Quantization with Outlier Tokens Tracing

Reference 97

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:46:04.863665Z

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 1095c688-020f-4cc9-a890-57c7c4a4f922 · inbound

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference cites this paper.

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference Accurate KV Cache Quantization with Outlier Tokens Tracing

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-20T20:33:43.298519Z

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 28514feb-dc3e-4535-8cb4-f46ed89f621c · 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 Accurate KV Cache Quantization with Outlier Tokens Tracing

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:15:19.938439Z

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.