Paper Citation Record · LEDGER

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models

As of 9 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 2 inbound Pith citation observations for arXiv:2506.03762.

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

pith.paper-citation-record.v1
2506.03762 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:02:06.917838Z

measured 49 of 49 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T01:46:59.423533Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T07:51:42.929093Z

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy1
unresolved46
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 69dd8e94-b4a0-4211-b58e-49f760feff90 · outbound

This paper cites GPT-4 Technical Report.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:04.003799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8559f0b-88f4-4183-aa06-31c74ca1227d · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:11.464740Z

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 aabd83b3-cc7b-4e50-9f55-f8802def6024 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:11.390738Z

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 1eeb90a9-8fdb-4f11-87d6-34825ff3ebf0 · outbound

This paper cites Longformer: The Long-Document Transformer.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:04.187212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83a85ce-42d4-40c1-822c-8ed43563f29f · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:11.313927Z

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 75173bb3-11c8-4430-9adb-a5f15cb29760 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:11.153489Z

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 e347d273-acc3-452f-8b09-474b9172bf9a · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:10.962742Z

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 3bfc0555-8c84-4e89-90c8-dd838e462077 · outbound

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

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:04.492749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a325a0-3b98-48b9-ae38-9429ab53e66f · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:04.585736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45e95a16-f62c-443a-b878-f57d3227c1fe · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:10.739655Z

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 ca4ff56c-4d27-45b7-9b94-4a023b1abd88 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:10.532130Z

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 6502974d-bbd1-4133-a642-7fab82bf8761 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:10.280933Z

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 c1821fb4-92d2-48d9-9751-cdaba51e04b1 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:10.135312Z

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 647faa00-2921-46eb-93b7-bfc513b49462 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.937719Z

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 dcbd14cb-276b-414b-b22b-170f1f54940a · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.861146Z

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 d053e91e-710e-41bd-b870-1d1f76e48ccd · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.737866Z

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 9b743bcb-7f80-4ede-9bea-5abdae2d9e1f · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.621684Z

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 a9a0313b-6712-4a20-9702-db0ec8c326eb · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.538400Z

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 bfa4c65c-cddd-4c25-b30c-97e4fd02fcd7 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.416255Z

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 5598f046-e2d8-41ee-b20d-47ffd407645f · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.297286Z

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 9a72b31f-abb7-4d65-8b6a-4ad67e9ce1e8 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.180353Z

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 29bf034c-e1ac-4b9e-9c32-faac74261ea5 · outbound

This paper cites World Model on Million-Length Video And Language With Blockwise RingAttention.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models World Model on Million-Length Video And Language With Blockwise RingAttention

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:05.405043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6520c81b-c9da-4760-9f14-80f303bacd70 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:09.103813Z

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 7dae47b3-0bd9-4acf-8601-1f08fed57a05 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.972313Z

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 83ab0304-5ead-4d1d-b007-c5602ad0e0f8 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.881021Z

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 f5890b33-39d8-4e31-ac62-0e81b2ceced8 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:05.627654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 553e2b68-acd7-44db-8d7d-1e93507fffe5 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.761317Z

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 bd752377-9f6c-4ccc-a8b8-fcd8d0ddd16f · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.678823Z

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 c0e8cf90-f4e9-4d22-b575-2d56dd548708 · outbound

This paper cites Transformers are Multi-State RNNs.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Transformers are Multi-State RNNs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:05.812475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa281451-1500-4aee-ae33-4f3ffc48bd67 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.599149Z

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 ed973358-054a-466a-8311-5d3d6b1cf73e · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.471813Z

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 4f10922c-c04a-4c5a-a166-354b5f22962d · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.325825Z

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 c0c83452-0e22-4701-aad2-3330d6e10f76 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.209876Z

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 374f3778-149e-4d28-a4f8-ba99f657bc62 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.102270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5590e404-6aa1-4b4e-aded-816a2f228aa6 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.103917Z

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 4827288d-3213-4595-80f2-56837cc95424 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:08.010386Z

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 021cd0f7-d840-47b3-8c66-3da4436da40f · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.253737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278d5873-5cb0-4a49-9743-51503a2c6db3 · outbound

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

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.316628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 506c2480-27e3-4056-99c5-e9f62e8b0607 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:07.849690Z

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 1846d53c-b3b9-4f6c-9bc2-48c605c6bd6b · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:07.720267Z

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 fe41da30-b4ae-4b58-9377-a0e081c01675 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:07.544416Z

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 ddc8d0ca-50c3-45ef-a434-20a8ff9bf490 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:07.398972Z

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 59ea2b8c-d92c-4212-a389-188e2193faa0 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.641375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cda7c7b-bc8c-4d0d-ace8-78f47016516f · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models OPT: Open Pre-trained Transformer Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.724922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7774c5cb-9d47-42bb-b53c-feb9af6ff620 · outbound

This paper cites an unresolved cited work.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:07.281279Z

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 ed8a2307-3cca-41af-84fe-97dbe00d64fe · outbound

This paper cites online" 'onlinestring :=.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models online" 'onlinestring :=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.827191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be8b3cef-6f92-474b-91ab-dd542f32483d · outbound

This paper cites write newline.

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models write newline

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:06.917838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 695d9391-85af-487c-bb26-f00175624c53 · inbound

Reformulating KV Cache Eviction Problem for Long-Context LLM Inference cites this paper.

Reformulating KV Cache Eviction Problem for Long-Context LLM Inference AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:10:53.504555Z

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 686cfe32-69bb-4571-80c5-46fe8e039912 · inbound

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression cites this paper.

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:51:42.940121Z

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.