Paper Citation Record · LEDGER

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing

As of 9 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2507.08045.

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

pith.paper-citation-record.v1
2507.08045 v2

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:46:59.928978Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

48 of 48 outbound references displayed

verified exact0
verified fuzzy5
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2ccea800-0bfb-4605-b35e-08beec07e739 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:03.822606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 44e30665-61fb-431b-86e8-7eb0e2606e48 · outbound

This paper cites Qwen Technical Report.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Qwen Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:56.492216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33b49590-1926-4f1d-bc75-271981ded03b · outbound

This paper cites LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:56.603147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8203924c-2727-42e8-a98a-78fcd41d8687 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:56.688329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 333690f5-25de-413b-8ae2-cd9a224816b8 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:03.624180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5773adbd-725b-4046-972a-1fbd142cdef5 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:03.445280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f0d8a101-94db-4d36-8653-a629a30dc0f0 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:03.258783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 52a5ec2a-5984-44cc-a45d-ba4b357ad6d5 · outbound

This paper cites MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:56.942562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b271f24-4e71-414d-8471-15a6a345ef12 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:03.100906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b18c5ea2-0999-4941-89d2-0ac9c15376d5 · outbound

This paper cites 2024.{Cost-Efficient} large language model serving for multi-turn conversations with{CachedAttention}.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing 2024.{Cost-Efficient} large language model serving for multi-turn conversations with{CachedAttention}

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:47:02.821233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 992e2d6e-5708-4f6a-bfd6-4f0fce634966 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:02.692408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7021283b-f1d0-4f7b-87bf-90266815e3c6 · outbound

This paper cites Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:57.357120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba078451-5b1f-48e8-81f5-06585fd2bf9a · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:02.578529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a1ff41ed-6cc8-4756-b45f-5b1bcf46addc · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:02.332678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 41843f4d-a06b-4137-95cb-584887bcee05 · outbound

This paper cites Compute Or Load KV Cache? Why Not Both?.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Compute Or Load KV Cache? Why Not Both?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:57.628851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e771c456-75f2-4223-b024-8ba4196aad8a · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:02.209071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e1ccf09-269e-406c-8f0c-1fdfc42dbb94 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:57.749067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 135d13cd-b265-468d-99ff-24c2ca2e5f97 · outbound

This paper cites 2024.{InfiniGen}: Efficient generative inference of large language models with dynamic {KV} cache management.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing 2024.{InfiniGen}: Efficient generative inference of large language models with dynamic {KV} cache management

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:47:02.092973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 39cb51da-041c-4adf-817d-e5b0e547102d · outbound

This paper cites DeepSeek-V3 Technical Report.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing DeepSeek-V3 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:57.888976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a6e164d-eedd-4a55-bb7e-1b6ffa3a5e31 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.983860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4ed0bed4-4301-4fb0-a9cc-2bcc33998b5f · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.870005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ed9c84bc-9bef-4cd9-b657-8ff4b421938c · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.077662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a3e00d3-f9ba-4313-8f02-51a19ce76b8b · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.776022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 26594bf7-e3eb-43b7-b420-b626c6ceaf8b · outbound

This paper cites How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.212120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bee1d5bb-3e17-47cd-ab24-21e5ab6ea404 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.285824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1755e2e1-63b6-4a39-8abc-da848c296c62 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.692227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a46d0626-f3d1-41c2-9bf3-6ebb9e2786a2 · outbound

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

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.428117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2a990ea-6325-4faf-9069-35641dbc51e2 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.498728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a34f8a2f-50c5-4dd8-b475-218c0303566b · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.514457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 914d7fb8-0528-495c-a05c-d582f7ac2648 · outbound

This paper cites Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.638674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 023a4cad-d3fb-49f1-aaf9-d9b00c4d299d · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.733703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2afa0d6-aa70-47a2-b4a8-3a10d64c8654 · outbound

This paper cites KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.887052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a7fa44-3138-486d-b4c6-89a3c69dcb21 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.955090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1575f78a-3e0e-46cf-9e9e-53a2aa88dbf3 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.347413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 84a97cef-a869-4dc6-a0dc-2037ab89439c · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:01.142115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 93c3ebc1-7c32-4929-a0cc-1e1b4d7491ca · outbound

This paper cites LLM as a System Service on Mobile Devices.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing LLM as a System Service on Mobile Devices

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:59.271032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 766c27fd-47a1-46c8-b055-f804703b5fe0 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:00.995186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4504ee79-7c86-4bd5-b9c8-e7c139bf2b1e · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:00.849400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e7cd3705-68b1-4274-9558-36d990f2f30a · outbound

This paper cites Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:59.177436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c43c1dfd-62bb-4985-b37d-0dcedd545423 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:00.617986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a248ac1f-e1a7-457a-9953-1938d397c8dd · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:47:00.487656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 20dc2fc9-2fc3-4328-8654-85bcc2146042 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:59.847372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac3c702c-004d-4adb-a072-f53b518ebd65 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:59.517709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efdb8c2b-6787-40a7-9219-4b0ef130181f · outbound

This paper cites In 2024 IEEE 40th International Conference on Data Engineering (ICDE).

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing In 2024 IEEE 40th International Conference on Data Engineering (ICDE)

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:47:00.726231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6601afc7-f3b1-48f5-8aeb-6cc250157a97 · outbound

This paper cites an unresolved cited work.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:59.928978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8084b7ab-afa5-450e-a029-24870962373e · outbound

This paper cites Advances in neural information processing systems 34 (2021), 15908–15919.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Advances in neural information processing systems 34 (2021), 15908–15919

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:47:02.455342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e1017d6d-e084-41d5-800d-3c55dc173870 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Efficient Streaming Language Models with Attention Sinks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T18:46:58.807261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecf8c95a-879e-4c25-8477-1973fd468bd8 · outbound

This paper cites Proceedings of the VLDB Endowment 17, 12 (2024), 4413–4416.

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing Proceedings of the VLDB Endowment 17, 12 (2024), 4413–4416

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:47:02.956220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.