Paper Citation Record · LEDGER

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads

As of 19 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 2 inbound Pith citation observations for arXiv:2501.15113.

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

pith.paper-citation-record.v1
2501.15113 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:41:05.147543Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T13:46:11.383126Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T09:05:58.128419Z

Reference resolution

40 of 40 outbound references displayed

verified exact1
verified fuzzy4
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f1ccdae-e7b5-4cef-8e8b-f67e4c96942d · outbound

This paper cites A Survey on In-context Learning.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads A Survey on In-context Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.955353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d1ecf5-b8b0-4265-b4ed-29df5387584e · outbound

This paper cites Tool Learning with Foundation Models.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Tool Learning with Foundation Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.960913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc862a5-ee84-42e3-912a-004898cd8962 · outbound

This paper cites Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.966169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14533b86-b51e-4d82-addf-15368f9c0ee1 · outbound

This paper cites StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-10T14:41:05.756449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e6a7c9b2-2294-41b9-89ab-29a9ed5c17a6 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.975704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 270c1694-f7a4-4dfa-9034-7966d0d99f3f · outbound

This paper cites BioRAG: A RAG-LLM Framework for Biological Question Reasoning.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads BioRAG: A RAG-LLM Framework for Biological Question Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.980455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50930c29-0d24-495e-8bad-822699b412e0 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads H2o: Heavy-hitter oracle for efficient generative inference of large language models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:41:05.898375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 187e3ac1-45a8-4e0c-bf85-be68c19a8dea · outbound

This paper cites LongHeads: Multi-Head Attention is Secretly a Long Context Processor.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads LongHeads: Multi-Head Attention is Secretly a Long Context Processor

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.989763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b5f45f-4193-4d29-8e0b-0f620fa8a31a · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Efficient Streaming Language Models with Attention Sinks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.994236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57cdb415-6c07-429c-8499-23a0f071df84 · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:04.999148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fdbb1a-83a3-4239-8abf-ed34e63c0914 · outbound

This paper cites PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.004324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f823a4-458b-4548-ba99-01702a53a02d · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads SnapKV: LLM Knows What You are Looking for Before Generation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.009013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de681a8d-578e-4497-80dd-db5200ce5d35 · outbound

This paper cites MiniCache: KV Cache Compression in Depth Dimension for Large Language Models.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.013818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ea337a1-1de8-4e1d-afe8-e223adcffd65 · outbound

This paper cites RazorAttention: Efficient KV Cache Compression Through Retrieval Heads.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.018480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1456b600-29f7-40ca-a27a-e6e4fdaa9894 · outbound

This paper cites Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.023298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 235de114-2b4d-43c0-abb4-a832ba9db4c8 · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.028215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 607948dc-9359-4ae5-865f-3496095887fc · outbound

This paper cites Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.032990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 789e0f0c-50b4-4f78-83da-a4edb2d57cdc · outbound

This paper cites Retrieval Head Mechanistically Explains Long-Context Factuality.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.037675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f11d050-6f92-435a-866d-782b30f4ade7 · outbound

This paper cites Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.045154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed73b555-b77c-477f-b1a9-17c3bbea4cdd · outbound

This paper cites A closer look at transformer attention for multilingual translation,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads A closer look at transformer attention for multilingual translation,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:41:05.882178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee253154-3d1c-4f8f-8b0e-8b4d4cb8fe7f · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.057591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ba6493-e27c-406f-9d64-b46f41054683 · outbound

This paper cites LooGLE: Can Long-Context Language Models Understand Long Contexts?.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads LooGLE: Can Long-Context Language Models Understand Long Contexts?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.062461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99270b41-2d38-46ef-8d8b-74b50b6801f7 · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.067310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6110563c-1c2d-486b-b5ed-1d8de218eb40 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.072104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b580b22-f8f7-4a8e-b9e6-df4079c13f8e · outbound

This paper cites Mistral 7B.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Mistral 7B

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.076675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab3992c-02fc-4d60-9a6d-428c0c80f4a7 · outbound

This paper cites InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.081285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867bfa47-cabe-46a9-ba94-c207f0001ed8 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.086383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 786dca31-1e67-458f-b3b7-48a54f0c473b · outbound

This paper cites Principal components analysis (pca),.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Principal components analysis (pca),

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.091154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c41285c-af47-4c36-b609-d3a2d7919af6 · outbound

This paper cites Attention is all you need,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Attention is all you need,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.095345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f70fda-990d-4de0-8647-57ce9d70a351 · outbound

This paper cites LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.099612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e611ed-2dce-4163-ace3-02824524d6e8 · outbound

This paper cites A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.103927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b405bba8-c603-490a-8238-e3786c687bc9 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.108203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52b249a-740e-4685-9fd1-f4255a219cc3 · outbound

This paper cites Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.112914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82fa0b58-9acb-4d82-833b-baeb2cc29240 · outbound

This paper cites QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.117333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 895f4727-556e-4266-8a88-567002d11549 · outbound

This paper cites Efficient Attentions for Long Document Summarization.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Efficient Attentions for Long Document Summarization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.122694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 350bfaf1-8983-4426-912c-d06967c507ac · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.127858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7a16d4-c105-48c2-a9e3-28962695ed2d · outbound

This paper cites Learning question classifiers,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Learning question classifiers,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:41:05.846991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ea4a1dda-b874-4ca7-9ea9-4d339c9e065f · outbound

This paper cites Exploiting semantic resources for large scale text categorization,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Exploiting semantic resources for large scale text categorization,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:41:05.830603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7a138ed5-73a8-4825-976e-86791e37726a · outbound

This paper cites RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.142575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c233d579-5980-4642-81ad-37da6ff46449 · outbound

This paper cites Longcoder: A long- range pre-trained language model for code completion,.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Longcoder: A long- range pre-trained language model for code completion,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.147543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1b23ff28-9c93-44f8-b1d1-d7b36a38705d · inbound

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification cites this paper.

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T13:46:11.383126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84eace44-4527-4779-9b34-87224001a7b8 · 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 Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:05:58.130976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.