Pith. sign in

Paper Citation Record · LEDGER

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse

As of 8 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2608.03893.

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

pith.paper-citation-record.v1
2608.03893 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:17:13.238301Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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 exact2
  • verified fuzzy1
  • unresolved9
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 04dfa064-c0a2-43b8-9fc6-10db9eb3cc33 · outbound

This paper cites Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.117220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.117220Z digest=sha256:eaa09642827eed484d6ba9c798f001eff07df214e4347af17932bd18f013a4b9

Observation 7a872c77-118b-447e-825f-ae1393e0d6ea · outbound

This paper cites an unresolved cited work.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-05T10:17:13.850996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-05T10:17:13.238301Z digest=sha256:e9afa5f625962dbe01ddf82559c40651c0cb1e6dc48682dbc0f6c93d9d6a5c46

Observation 059622a7-25a0-42a6-9b86-5b509c963da3 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.151492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.151492Z digest=sha256:1fd7ad661ed41ac72a57b4056422728710ebb9a07388a6dceeba5f1643fa5ce7

Observation 9d3efb20-75e8-4a07-a077-f86d64862a89 · outbound

This paper cites The Llama 3 Herd of Models.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse The Llama 3 Herd of Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.185214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.185214Z digest=sha256:50afc0d46d5d3b2aaf9d72d947376217219b8faeb1e7a42a8a7032cb856c1f5a

Observation a2c90072-5447-4599-a095-d3e3583d956f · outbound

This paper cites Cross-family speculative prefill: Training-free long-context compression with small draft models.arXiv preprint arXiv:2603.02631,.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Cross-family speculative prefill: Training-free long-context compression with small draft models.arXiv preprint arXiv:2603.02631,

Reference 8

Resolution
verified exact
raw_fallback, observed 2026-08-05T10:17:13.552285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-05T10:17:13.196576Z digest=sha256:13a505f90e2dbbd5f788793f196728011b347e7f82ee183f139c54f8e3e92432

Observation b4587dee-5401-4498-9b35-423e98cc0b9c · outbound

This paper cites Qwen3 Technical Report.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Qwen3 Technical Report

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.225487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.225487Z digest=sha256:7d9d62992563069e0641303516183b60d63e3f57e9cfe1c72d4ea06295d16831

Observation 373c7d5e-858d-4b19-80ba-73e8536d1676 · outbound

This paper cites − all RoPE.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse − all RoPE

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T10:17:13.890044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-05T10:17:13.231950Z digest=sha256:60d829e6e71ac2c37d48b54fb1d04dff4cd601d9367fddfcf3f8629105906d7f

Observation 57f07367-e1b7-4373-8545-642bac31128b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Training Verifiers to Solve Math Word Problems

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.160259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.160259Z digest=sha256:0cb82b6c8df49070388209ba08247b02616a9773580d4820c80d9c1ae951c87a

Observation 195e8f55-2605-45aa-b323-d8d9d98ec209 · outbound

This paper cites Dery, Zohar Yahav, Henry Prior, Qixuan Feng, Jiajun Shen, and Arthur Szlam.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Dery, Zohar Yahav, Henry Prior, Qixuan Feng, Jiajun Shen, and Arthur Szlam

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.173613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.173613Z digest=sha256:db1e879fd0d4849206f48de4b99c2625dd414c2bc922d968c272c5dbe34335da

Observation 75bd6c27-d7aa-4d8f-a21c-58c93c7e00ab · outbound

This paper cites ICaRus: Identical cache reuse for efficient multi-model inference.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse ICaRus: Identical cache reuse for efficient multi-model inference

Reference 2022

Resolution
verified exact
raw_fallback, observed 2026-08-05T10:17:13.455652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-05T10:17:13.219675Z digest=sha256:2095f76cb9d9f2233eba26a394d897daeb57b085930d389115305e96a4723d77

Observation 28732b28-1bca-497d-b0b4-51481a81a173 · outbound

This paper cites xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.142422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.142422Z digest=sha256:3a94a0a6257c0952a148f94667910b8d4d9290876c9ae7a65a3e7b0cc540e5d8

Observation 868c2fd9-5669-4f4d-8e8c-ada42d548475 · outbound

This paper cites NVIDIA Nemotron 3: Efficient and Open Intelligence.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse NVIDIA Nemotron 3: Efficient and Open Intelligence

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-05T10:17:13.131739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:17:13.131739Z digest=sha256:eefb14e066d46d93596bc033822a70790b9c23c821a5e0dd28ce89ec9cd81d37

Pith citing papers

No inbound Pith citation observations are available.