Paper Citation Record · LEDGER

Decouple and Cache: KV Cache Construction for Streaming Video Understanding

As of 19 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2605.01858.

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

pith.paper-citation-record.v1
2605.01858 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T14:47:54.917408Z

measured 20 of 20 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T12:28:00.885137Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

19 of 19 outbound references displayed

verified exact12
verified fuzzy1
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 27b29a5d-81b8-479e-8e4a-c7c3431e3540 · outbound

This paper cites Qwen2.5-VL Technical Report.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Qwen2.5-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T11:31:03.544517Z

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 aae0a56c-695d-47e3-9cfc-69be4f57db2e · outbound

This paper cites Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T11:31:03.596964Z

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 bb0993fe-c244-4af7-ab40-485b7c61345d · outbound

This paper cites Extending Context Window of Large Language Models via Positional Interpolation.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Extending Context Window of Large Language Models via Positional Interpolation

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:20:58.016961Z

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 c43ba94c-104b-4986-8759-33939e277c70 · outbound

This paper cites ViSpeak: Visual Instruction Feedback in Streaming Videos.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding ViSpeak: Visual Instruction Feedback in Streaming Videos

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:03.582625Z

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 366c7205-f8de-4192-b100-b535d2072998 · outbound

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

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Lm-infinite: Zero-shot extreme length generalization for large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:46:19.677859Z

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 912e9849-5a85-46c4-ada0-1164ec692f17 · outbound

This paper cites Infinipot-v: Memory-constrained kv cache com- pression for streaming video understanding.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Infinipot-v: Memory-constrained kv cache com- pression for streaming video understanding

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:03.592378Z

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 f52bea55-7459-4551-a43f-d5c408a2e669 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding LLaVA-OneVision: Easy Visual Task Transfer

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T11:31:03.558420Z

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 eb3684ab-300c-44e6-a7d0-7b730bf49737 · outbound

This paper cites StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T11:31:03.575498Z

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 f391ef84-cbb1-40bb-bf2f-1326a2d7e83a · outbound

This paper cites Lost in the Middle: How Language Models Use Long Contexts.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Lost in the Middle: How Language Models Use Long Contexts

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T11:31:03.570719Z

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 813374e9-2614-4a74-b24e-6d7c58b750b5 · outbound

This paper cites LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-11T11:31:03.587336Z

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 6ce05c96-c77c-4e1f-be56-354d722a8297 · outbound

This paper cites On discrim- inative vs.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding On discrim- inative vs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:03.612285Z

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 c3db2087-ef04-4486-b0e0-84246ad47a2e · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:01:23.440331Z

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 9e0f6efa-4005-45a8-85ac-57d3c18dbf16 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T11:31:03.649723Z

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 ca99b3bd-dc4e-42e5-86f6-5928c1a9bfbf · outbound

This paper cites Streambridge: Turning your offline video large language model into a proactive streaming assistant.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Streambridge: Turning your offline video large language model into a proactive streaming assistant

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:03.617054Z

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 b94c4bb3-fada-4c4a-909f-4b6b4acbe0cd · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Efficient Streaming Language Models with Attention Sinks

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-11T11:31:03.621621Z

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 63a5bf8b-564b-42e9-a4b0-665af66bd598 · outbound

This paper cites StreamingVLM: Real-Time Understanding for Infinite Video Streams.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding StreamingVLM: Real-Time Understanding for Infinite Video Streams

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:51:33.451476Z

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 f4b025e5-d85a-49d5-9bda-3efef210333c · outbound

This paper cites StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T11:31:03.635026Z

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 09c9c0bb-1fff-461f-aa8e-83141dc06e75 · outbound

This paper cites Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:03.562532Z

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 df74d09c-8af0-4303-a424-24aa76a10d28 · outbound

This paper cites an unresolved cited work.

Decouple and Cache: KV Cache Construction for Streaming Video Understanding Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:46:19.673538Z

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.

Pith citing papers

Observation 9a879610-a4d1-493d-9ec5-98b5baa78904 · inbound

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning cites this paper.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning Decouple and Cache: KV Cache Construction for Streaming Video Understanding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.885137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.