Paper Citation Record · LEDGER

TreeKV: Smooth Key-Value Cache Compression with Tree Structures

As of 19 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2501.04987.

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

pith.paper-citation-record.v1
2501.04987 v3

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:25:41.263764Z

measured 20 of 20 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 2026-05-25T05:22:47.198185Z

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

19 of 19 outbound references displayed

verified exact2
verified fuzzy6
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 13249a16-4898-49e2-897a-b2384ff1a02c · outbound

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

TreeKV: Smooth Key-Value Cache Compression with Tree Structures LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.184029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f816662-2fec-41ad-b882-abfc390e248a · outbound

This paper cites Fovea transformer: Efficient long- context modeling with structured fine-to-coarse attention.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Fovea transformer: Efficient long- context modeling with structured fine-to-coarse attention

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:25:41.497499Z

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 8c59361b-24f1-4654-866b-3306be04ffc5 · outbound

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

TreeKV: Smooth Key-Value Cache Compression with Tree Structures SnapKV: LLM Knows What You are Looking for Before Generation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.207753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 190725d9-cfae-4434-b4d1-5cf7de266738 · outbound

This paper cites Scissorhands: Ex- ploiting the persistence of importance hypothesis for llm kv cache compression at test time.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Scissorhands: Ex- ploiting the persistence of importance hypothesis for llm kv cache compression at test time

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:25:41.485876Z

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 849a4dc2-1d8c-4b61-82e4-264473520e45 · outbound

This paper cites Transformers are Multi-State RNNs.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Transformers are Multi-State RNNs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.217872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21a53ee0-b0f2-4a00-9062-ea2bb4d60a09 · outbound

This paper cites Efficiently Scaling Transformer Inference.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Efficiently Scaling Transformer Inference

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.222232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0722134c-c233-483e-a82e-cf3b0b16dde2 · outbound

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

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.235020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5ef0d8-8bcc-4ca3-9e7d-5bff92880aae · outbound

This paper cites XL3M: A Training-free Framework for LLM Length Extension Based on Segment-wise Inference.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures XL3M: A Training-free Framework for LLM Length Extension Based on Segment-wise Inference

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-10T21:25:41.365416Z

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 4640a3ee-65b7-4fa3-b7ac-ce1d9d7c65b2 · outbound

This paper cites Emergent Abilities of Large Language Models.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Emergent Abilities of Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.243369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a28cf18-7be0-4a91-978a-55fddae9a59b · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Efficient Streaming Language Models with Attention Sinks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.247199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f328f19a-bac3-4371-a5a2-5be7ba46d374 · outbound

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

TreeKV: Smooth Key-Value Cache Compression with Tree Structures PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.251024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccf65406-15a8-4fd6-99d9-8c62d77eabb1 · outbound

This paper cites Wordcraft: story writing with large language models.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Wordcraft: story writing with large language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:25:41.460099Z

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 d8f20272-7c65-4af9-bc55-b153cc589812 · outbound

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

TreeKV: Smooth Key-Value Cache Compression with Tree Structures PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.259363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b9bb5f5-4c87-4d8e-8436-cb214ba38d77 · outbound

This paper cites Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-10T21:25:41.300916Z

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 446196d6-41b3-4c73-aad2-395029588609 · outbound

This paper cites Dct-former: Ef- ficient self-attention with discrete cosine transform.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Dct-former: Ef- ficient self-attention with discrete cosine transform

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:25:41.472839Z

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 c5134423-3603-4ed4-9398-fbd81f21396a · outbound

This paper cites Lm-infinite: Zero-shot extreme length generalization for large language models.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Lm-infinite: Zero-shot extreme length generalization for large language models

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:25:41.520981Z

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 9b06ccb0-9493-47e3-b08e-7f30e7dd07d7 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Compressive Transformers for Long-Range Sequence Modelling

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.226478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c5e47fb-a107-442b-814a-04f0c8996f85 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T21:25:41.189033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e15347ef-a648-42a0-80fb-ab0498bcfb55 · outbound

This paper cites Fourier transformer: Fast long range mod- eling by removing sequence redundancy with fft operator.

TreeKV: Smooth Key-Value Cache Compression with Tree Structures Fourier transformer: Fast long range mod- eling by removing sequence redundancy with fft operator

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:25:41.508151Z

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 7a0673d6-ba0f-47f9-ba61-5c114be5d4de · inbound

Adaptive Mass-Segmented KV Compression for Long-Context Reasoning cites this paper.

Adaptive Mass-Segmented KV Compression for Long-Context Reasoning TreeKV: Smooth Key-Value Cache Compression with Tree Structures

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:25:22.841372Z

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.