Paper Citation Record · LEDGER

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning

As of 18 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2607.19547.

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

pith.paper-citation-record.v1
2607.19547 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T12:28:01.095654Z

measured 12 of 12 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 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

12 of 12 outbound references displayed

verified exact0
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 091b917d-4af3-4e39-ad04-42dda6873dae · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.353684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06db601-c8c5-4c3f-b74e-5a6a77b6d731 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.410190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 229ac330-5582-426c-83fa-8ba27db2ed37 · outbound

This paper cites Qwen2.5-VL Technical Report.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.448398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b9e2877-9aea-4ef6-8e25-09bd88ffac98 · outbound

This paper cites KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse,.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.506628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d3325fe-e246-4ec7-aae0-c9af654fcc86 · outbound

This paper cites CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.559569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92ec888c-a00e-41f2-be75-b0ea86ce5fcc · outbound

This paper cites Streaming Video Question-Answering with In-context Video KV-Cache Retrieval.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning Streaming Video Question-Answering with In-context Video KV-Cache Retrieval

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.614741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed03f78e-bddd-4263-9b3f-fd4ded9ce9be · outbound

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

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.676672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f908bde8-49e7-48ac-8df0-218143f62d5d · outbound

This paper cites StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression,.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.743674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd4feeb3-aec0-4ae2-bbb9-7012c9f0416f · outbound

This paper cites HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.825262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Decouple and Cache: KV Cache Construction for Streaming Video Understanding.

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.

Observation ac47fea1-aa70-403c-8d35-88a576e228ee · outbound

This paper cites VideoRoPE: What Makes for Good Video Rotary Position Embedding?.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.977584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9730513-f4ac-4e65-ab9d-b9823f66a968 · outbound

This paper cites TempCompass: Do Video LLMs Really Understand Videos?.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning TempCompass: Do Video LLMs Really Understand Videos?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:01.095654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.