Paper Citation Record · LEDGER

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing

As of 10 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2604.22782.

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

pith.paper-citation-record.v1
2604.22782 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T19:56:48.015363Z

measured 27 of 27 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T03:07:23.648382Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

26 of 26 outbound references displayed

verified exact18
verified fuzzy4
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

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

Outbound references

Observation 8ab9b373-3384-4d28-961a-646cc847ef6a · outbound

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

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.035439Z

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 0edfe695-86b3-496d-bc14-322927dd5f9e · outbound

This paper cites Qwen3 Technical Report.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Qwen3 Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.032409Z

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 5810c075-62f7-4771-8a1b-62be82877a59 · outbound

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

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.038555Z

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 07582ff8-17c6-4436-9058-bce04afff524 · outbound

This paper cites OracleKV: Oracle guidance for question-independent KV cache compression.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing OracleKV: Oracle guidance for question-independent KV cache compression

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T19:58:12.875399Z

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 c9877530-9659-4d33-8bda-7773d3b72b3c · outbound

This paper cites Joao Monteiro, Étienne Marcotte, Pierre-Andre Noel, Valentina Zantedeschi, David Vazquez, Nicolas Chapados, Christopher Pal, and Perouz Taslakian.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Joao Monteiro, Étienne Marcotte, Pierre-Andre Noel, Valentina Zantedeschi, David Vazquez, Nicolas Chapados, Christopher Pal, and Perouz Taslakian

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T19:58:12.881688Z

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 0afe267d-674f-4f95-8d75-5f91593e0c76 · outbound

This paper cites Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.051857Z

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 5b1485e0-a9a8-4d07-b8c8-e874b5eb4e3b · outbound

This paper cites Kvzip: Query-agnostic kv cache compression with context reconstruction.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Kvzip: Query-agnostic kv cache compression with context reconstruction

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.069460Z

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 334b04c0-2247-4f67-8844-c82d39b4b234 · outbound

This paper cites Multipole attention for efficient long context reasoning.arXiv preprint arXiv:2506.13059.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Multipole attention for efficient long context reasoning.arXiv preprint arXiv:2506.13059

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.045218Z

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 c81d3186-3a51-4fb1-9d4a-4e6bf6527521 · outbound

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

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:11:21.895994Z

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 b8f667ce-87fe-422c-a295-ef3880e7501a · outbound

This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.075939Z

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 d93bf77b-c884-4512-960f-d3027ae1ccc6 · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T23:49:11.451207Z

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 a17824ea-0758-4938-a708-8f4afa56a0eb · outbound

This paper cites NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:02:08.433616Z

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 778a8ef3-9e27-48c4-9f08-88ce35c1e6f7 · outbound

This paper cites Longformer: The Long-Document Transformer.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Longformer: The Long-Document Transformer

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.079047Z

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 784c6ec5-cb6e-4919-ae56-855b5c9ad0b9 · outbound

This paper cites Rattention: Towards the minimal sliding window size in local-global attention models.arXiv preprint arXiv:2506.15545, 2025a.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Rattention: Towards the minimal sliding window size in local-global attention models.arXiv preprint arXiv:2506.15545, 2025a

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.048401Z

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 af04703c-55f0-4797-beab-463648deeb1d · outbound

This paper cites A systematic study of cross-layer kv sharing for efficient llm inference.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing A systematic study of cross-layer kv sharing for efficient llm inference

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T19:58:12.879232Z

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 b7b07a52-6bfb-4bff-9057-6c6ab6de38ce · outbound

This paper cites CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.082192Z

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 9ca94b20-741a-4430-a400-9740ee495251 · outbound

This paper cites Cross-layer attention sharing for large language models.arXiv preprint arXiv:2408.01890.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Cross-layer attention sharing for large language models.arXiv preprint arXiv:2408.01890

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.058971Z

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 7351aec5-c8c2-4627-b739-ae141d653acf · outbound

This paper cites Reducing Transformer Depth on Demand with Structured Dropout.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Reducing Transformer Depth on Demand with Structured Dropout

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:58:12.041938Z

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 52a89e88-9964-4806-9a81-b1e4c41e5c9b · outbound

This paper cites Decoupled Weight Decay Regularization.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Decoupled Weight Decay Regularization

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.065886Z

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 a5c43318-42b6-4b39-bda0-bf9b3cb09b41 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Training Compute-Optimal Large Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.091924Z

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 55a4d090-0284-4d4a-a10b-505725ba4ec3 · outbound

This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T19:58:12.883711Z

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 1af6aa97-9e58-4d3c-8500-1349f8526727 · outbound

This paper cites Know What You Don't Know: Unanswerable Questions for SQuAD.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Know What You Don't Know: Unanswerable Questions for SQuAD

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.088803Z

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 e876b51d-40a7-4b8e-822d-daf3a2730fa1 · outbound

This paper cites MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.094981Z

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 8f816c2a-459a-4140-8e13-25daea30d156 · outbound

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

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:58:12.098038Z

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 e463a1f5-d984-4cf3-ac70-fe537978773b · outbound

This paper cites Mistral 7B.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Mistral 7B

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T19:58:12.072910Z

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 6c5586f2-af8e-4251-adbf-9a4d47579a87 · outbound

This paper cites an unresolved cited work.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-05-13T19:58:12.877265Z

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.

Pith citing papers

Observation 37a1c611-21de-4e44-ad22-2d447f8121fe · inbound

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression cites this paper.

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing

Reference 86

Resolution: verified exact; local_arxiv, observed 2026-07-08T03:14:31.557994Z

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.