Paper Citation Record · LEDGER

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding

As of 24 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2606.29207.

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

pith.paper-citation-record.v1
2606.29207 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T02:54:11.777615Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:15:32.250856Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T15:15:32.457802Z

Reference resolution

45 of 45 outbound references displayed

verified exact14
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier3
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe7376e2-ea5a-4d37-add5-09056dfb6d34 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d25d1953-9c09-4cf4-b309-3134ed018d6f · outbound

This paper cites CONCUR: High-throughput agentic batch inference of LLM via congestion-based concurrency control.arXiv preprint arXiv:2601.22705.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding CONCUR: High-throughput agentic batch inference of LLM via congestion-based concurrency control.arXiv preprint arXiv:2601.22705

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.254956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 41dcbe9c-0c08-4e4a-8bfc-9dd7f5679af0 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d67e1e4d-a683-4286-9711-5432ebc161c2 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c54d6505-605c-4cab-b07d-925fb5e10c9e · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa50a89c-e5bf-42d4-93b2-81e8cde0ac98 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c73c01-3186-4420-936d-086af705281e · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a512c8-266f-4b28-bc4b-4202f6ce6f64 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.212475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 997d0580-e239-4e76-b7b6-b1f78961ae40 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef9aefc8-c8cb-4722-b9f5-3ab05fb142b0 · outbound

This paper cites MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.223576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c6592f79-3a9c-43b3-88c1-430de1a4073c · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54628fc8-b21f-4a37-a66b-2aea8d0c9c70 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.237137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 66e6b0dd-2217-4ded-8784-54051512ebd8 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Gonzalez, Hao Zhang, and Ion Stoica

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35c3e917-cc1a-4083-9fb4-bdabff066576 · outbound

This paper cites In Proceedings of the 29th Symposium on Operating Systems Principles (SOSP ’23).

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding In Proceedings of the 29th Symposium on Operating Systems Principles (SOSP ’23)

Reference 14

Resolution: malformed identifier; arxiv_id, observed 2026-06-30T03:04:14.265268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f1d38012-a07f-4c57-9e7d-ee67d6f3bd26 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c43c7c5-d02a-4706-991e-1671fce3e692 · outbound

This paper cites Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.208841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c1967422-3b95-4e7e-a473-9e005a47b312 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e0773b8-588a-4436-879a-bfb7559130d1 · outbound

This paper cites DeepSeek-V3 Technical Report.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding DeepSeek-V3 Technical Report

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T03:04:14.260714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a13546a9-8d61-4240-8055-2ed2fa3a89a5 · outbound

This paper cites Ring Attention with Blockwise Transformers for Near-Infinite Context.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Ring Attention with Blockwise Transformers for Near-Infinite Context

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.219523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d97db2e-18fc-40d2-82f1-6101e92a8ea3 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T03:04:14.180328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6ad5adf1-b131-4df4-b2a7-108f7e5543d1 · outbound

This paper cites Online normalizer calculation for softmax.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Online normalizer calculation for softmax

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.188442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d3bea937-a7f7-4853-878c-7318feead93e · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be2a688-cb7b-4fec-a2f5-39d79eab3378 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 949f75b8-5c44-477d-b819-b7363f75e0a9 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding MemGPT: Towards LLMs as Operating Systems

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.176459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 12256fb6-6ec4-4136-8c02-12093833f48a · outbound

This paper cites Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Anselm Lev- skaya, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Anselm Lev- skaya, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T03:04:13.705243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dce82fe2-6899-4a76-ab18-64fb9f9c6ed0 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7987c3ea-151d-40bc-a969-6c3bbda62804 · outbound

This paper cites https://vllm.ai/blog/2026-05-06-mooncake-store.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding https://vllm.ai/blog/2026-05-06-mooncake-store

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4691849d-b3a1-4113-8de7-04fdc8835d0d · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 28

Resolution: malformed identifier; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8803a508-7e19-4ba7-811a-5f1fe3f14b7a · outbound

This paper cites Graham Lopez, Matthew B.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Graham Lopez, Matthew B

Reference 29

Resolution: malformed identifier; doi_truncated, observed 2026-06-30T03:04:13.700088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ac1f5f37-f81c-439b-a554-f53a4a86c4e2 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7a581e-0f5a-4451-b6c0-6a1410b0eb13 · outbound

This paper cites InProceedings of the 40th Interna- tional Conference on Machine Learning (ICML).

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding InProceedings of the 40th Interna- tional Conference on Machine Learning (ICML)

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89db038f-bc64-4bd1-b001-471606a21070 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.170976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3e56425c-2ba6-40b1-a5f4-ae240261e427 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 683ca576-4ec4-45a9-9f5f-cab250b9ccd5 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58ecf3bc-65b8-4c89-a3fc-f269709113c8 · outbound

This paper cites In Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP '24), 2024.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding In Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP '24), 2024

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T03:04:13.710550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8bd74438-9350-4275-8799-d942ac98399f · outbound

This paper cites Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.196446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 68e52c3a-1e87-489d-b804-53d02e36f54a · outbound

This paper cites Dualpath: Breaking the storage bandwidth bottleneck in agentic llm inference.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Dualpath: Breaking the storage bandwidth bottleneck in agentic llm inference

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.268305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 72ba9c36-d2ef-4cd3-b4ad-99e46bb75ca7 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 744dfe47-89ce-4be2-8d8f-d136776e890b · outbound

This paper cites Context Parallelism for Scalable Million-Token Inference.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Context Parallelism for Scalable Million-Token Inference

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.241549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cd4cdba3-61b5-4074-8bc8-58af2c9433b1 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81ff348b-798b-41ed-977c-18c2823e3782 · outbound

This paper cites LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.246323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ab2abf9a-5406-47af-a8cd-c6d589012baf · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3686bac-6a97-44b2-aa8e-c88c48e7e763 · outbound

This paper cites InAdvances in Neural Information Processing Systems (NeurIPS).

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding InAdvances in Neural Information Processing Systems (NeurIPS)

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fb983a1-5fff-4a43-b385-770b646b6d69 · outbound

This paper cites an unresolved cited work.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-30T02:54:11.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a52402-1472-4cb6-9520-55da65adaea6 · outbound

This paper cites MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism.

KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.249359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 6544083a-6474-4221-a945-1dae82860697 · inbound

Zellige: Moldable Sequence Placement for Mixed Image-Video DiT Training cites this paper.

Zellige: Moldable Sequence Placement for Mixed Image-Video DiT Training KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:15:32.461915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.