Paper Citation Record · LEDGER

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry

As of 17 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 1 inbound Pith citation observation for arXiv:2608.06849.

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

pith.paper-citation-record.v1
2608.06849 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:44:35.835963Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:15:48.991022Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-14T04:15:49.096065Z

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy11
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2baa8a96-9d7a-421d-846b-eb1b1f0ebc28 · outbound

This paper cites arXiv preprint arXiv:2602.03560 , year=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry arXiv preprint arXiv:2602.03560 , year=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.642890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 786adb56-7bab-40c8-acd0-077e75c335b8 · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads , url =.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads , url =

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.869167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cda04c08-d434-4f83-8b1e-f790187b437e · outbound

This paper cites arXiv preprint arXiv:2602.04541 , year=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry arXiv preprint arXiv:2602.04541 , year=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.654506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5377e7a1-0dae-4a69-a803-9f316acf1822 · outbound

This paper cites arXiv preprint arXiv:2512.16391 , year=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry arXiv preprint arXiv:2512.16391 , year=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.658664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 251ce26f-15bf-4f23-b341-74b4f142b2cc · outbound

This paper cites TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention , url =.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention , url =

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.857109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 34cb0297-2d70-4e6e-8930-d50cc24d0c26 · outbound

This paper cites arXiv preprint arXiv:2603.12201 , year=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry arXiv preprint arXiv:2603.12201 , year=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.668007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc684d6-1fac-43a8-a417-ea18ce4da16a · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.672325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bcf13e1-0960-4e5a-beec-6ceb664bb4a8 · outbound

This paper cites arXiv preprint arXiv:2603.13314 , year=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry arXiv preprint arXiv:2603.13314 , year=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.675906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5382df52-881f-4cc6-bf0d-ca7890dd6284 · outbound

This paper cites Qwen2.5 Technical Report.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Qwen2.5 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.679427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2e1a930-1fad-4aca-be04-64ecf0be25bd · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.683757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b204c8-0da1-43dd-96bf-10b2f72628a7 · outbound

This paper cites https://www.anthropic.com/engineering/building-effective-agents , year=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry https://www.anthropic.com/engineering/building-effective-agents , year=

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.842789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c589a056-3e06-4f5c-995c-4ac402fc9541 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in Neural Information Processing Systems , volume=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.691848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9503d981-62af-4a7d-b25c-49bd3461ac8a · outbound

This paper cites D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.695799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d61c39c-110e-49ec-bc3d-c7d85889c825 · outbound

This paper cites Sliding Window Attention Training for Efficient Large Language Models.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Sliding Window Attention Training for Efficient Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.700092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2247790e-36a6-4e37-870c-b4a359832b3e · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in Neural Information Processing Systems , volume=

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.819151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4863f428-27e8-49ec-90fb-936c60c6f781 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in Neural Information Processing Systems , volume=

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.806555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2e44d7c7-b451-45d7-be05-66f9871912c0 · outbound

This paper cites The Llama 3 Herd of Models.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry The Llama 3 Herd of Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.712318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b22a25d-6072-4bd3-bae0-f3582aa00f59 · outbound

This paper cites Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.718471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5c55004-16dc-4732-b785-ccde5bfa676e · outbound

This paper cites Advances in neural information processing systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in neural information processing systems , volume=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.723367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5f38f2-ed3d-4bd9-bdab-4e881a67a06b · outbound

This paper cites Generalizations of Sylvester's determinantal identity.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Generalizations of Sylvester's determinantal identity

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-08-10T19:44:35.988602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 09e19945-f070-4d14-8a65-f47181b4d43e · outbound

This paper cites Advances in neural information processing systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in neural information processing systems , volume=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.732282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3bee1a0-e987-4232-bb2c-c0e13bc61cfd · outbound

This paper cites Longformer: The Long-Document Transformer.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Longformer: The Long-Document Transformer

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.736618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8bd2e13-f82b-466d-9012-57f16914b3d5 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in Neural Information Processing Systems , volume=

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.764310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6d4a9e6c-ac44-48d2-ac33-64b3f8fc31e2 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks , url =.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Efficient Streaming Language Models with Attention Sinks , url =

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.745592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27b4b91e-6d33-4616-9439-31575493a62a · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in Neural Information Processing Systems , volume=

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.743057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7221584d-8357-49d7-8281-3bca7ca1802a · outbound

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

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.753794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaf438dc-bf41-43d0-9b1a-74b9aad4cbda · outbound

This paper cites CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.760151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86e16be4-d1e6-49c4-bbb6-2a91a7dfaadc · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.764980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3816af21-e8cb-4dcb-96ab-b59d43e47ad2 · outbound

This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.770378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3c7146a-2b83-4ac1-a07b-b4bce6ebaf33 · outbound

This paper cites Qwen3 Technical Report.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Qwen3 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.774721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce472bd-9dcb-4ead-8cff-b1ba68562c9e · outbound

This paper cites 2026 , howpublished=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry 2026 , howpublished=

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.721978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3354449a-4964-40d9-b868-d039b6b55524 · outbound

This paper cites Neurocomputing , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Neurocomputing , volume=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.784770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f4dc911-b628-4881-8b09-df5574e2651d · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation , url =.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry SnapKV: LLM Knows What You are Looking for Before Generation , url =

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.790099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b46b94c-f2a6-4420-aae1-f4c28c64570a · outbound

This paper cites 2024 , cdate=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry 2024 , cdate=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.697591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 56809ac4-a57f-435c-aa9e-4185a153817d · outbound

This paper cites RazorAttention: Efficient.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry RazorAttention: Efficient

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.680615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8f7f343c-c3d4-45b4-9c4f-3fb85facbc2a · outbound

This paper cites NACL : A General and Effective KV Cache Eviction Framework for LLM at Inference Time.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry NACL : A General and Effective KV Cache Eviction Framework for LLM at Inference Time

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.804930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db61237-7085-4db7-9169-06198db0242e · outbound

This paper cites Multi-Head Attention: Collaborate Instead of Concatenate.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Multi-Head Attention: Collaborate Instead of Concatenate

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.809431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f7353c-d3e2-4448-a8eb-c44e02803f13 · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.815239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 785cf5ae-4205-405b-8700-e02012b15afa · outbound

This paper cites Proceedings of the 29th symposium on operating systems principles , pages=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Proceedings of the 29th symposium on operating systems principles , pages=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.819645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d489b36-26ea-463f-b372-ff4f19fd222d · outbound

This paper cites Advances in neural information processing systems , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Advances in neural information processing systems , volume=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.823398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84d18435-2480-4c67-bf33-9c529435f7d1 · outbound

This paper cites Transformers: State-of-the-Art Natural Language Processing.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Transformers: State-of-the-Art Natural Language Processing

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.826661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4fed672-5e7e-405c-9867-b478d8e61a0e · outbound

This paper cites 2007 15th European signal processing conference , pages=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry 2007 15th European signal processing conference , pages=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:35.831385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1e67c36-c69e-4f7e-adbc-b562a825a4b4 · outbound

This paper cites Journal of the ACM (JACM) , volume=.

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Journal of the ACM (JACM) , volume=

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:36.623124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 2fa83f69-0a2a-455f-85ae-b57810537f32 · inbound

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference cites this paper.

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:15:49.105871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.