Paper Citation Record · LEDGER

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference

As of 9 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2506.02572.

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

pith.paper-citation-record.v1
2506.02572 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:26:02.274620Z

measured 42 of 42 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:45:48.458849Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T00:45:48.747511Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d00d6d16-d450-434f-9c50-f55eeaeb2bb2 · outbound

This paper cites online" 'onlinestring :=.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:57.349731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0264211-adc8-4dcf-9e69-f46c3df0a536 · outbound

This paper cites write newline.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:57.459565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ab32b5-96e1-4cf7-8a59-a4db1e863739 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:57.675401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef753db-df26-4f3a-ad33-345fced6e436 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:57.843590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5258d014-ba2d-4a4b-b4e7-f30b0cc1acb1 · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:57.958618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9867a5ec-f2d4-463f-bc37-ca11d9540298 · outbound

This paper cites LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:58.070396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a455538b-71a8-48d8-88b4-fa44995695e9 · outbound

This paper cites MagicPIG: LSH Sampling for Efficient LLM Generation.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference MagicPIG: LSH Sampling for Efficient LLM Generation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:58.308531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e84205aa-0633-4f08-9907-660047ea07d1 · outbound

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

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:58.446766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b527f51-05cf-4587-8bc5-3bf20c84f762 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:58.692270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab5eca77-3f83-46e3-8a11-8324063aa0d8 · outbound

This paper cites HashAttention: Semantic Sparsity for Faster Inference.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference HashAttention: Semantic Sparsity for Faster Inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:58.886175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af753a9a-dbfa-4988-8115-d17d67229f61 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:06.014550Z

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 8629c365-fbe6-4024-9823-fe469e099adb · outbound

This paper cites Memory-efficient Transformers via Top-$k$ Attention.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Memory-efficient Transformers via Top-$k$ Attention

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:59.218497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19c23bce-5875-44f6-92fb-259f5d75ee64 · outbound

This paper cites KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:59.316579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98153a66-8728-42ce-93cd-e39469ce9dac · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:59.386831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6999e4-445f-4533-874c-ec85146d0447 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:05.794332Z

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 1edc92a5-580a-4b71-85b4-741ef6a3ddd3 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:05.546700Z

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 02e562ac-2889-411f-b68f-268dde24cd2e · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:59.706591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 012433c7-92dc-48a1-aabe-e548db1efe5e · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:05.347082Z

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 37306390-c055-4a70-999b-5d757f92dd6c · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:25:59.949662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 098a8c1b-004e-4148-b148-d46686046608 · outbound

This paper cites DeepSeek-V3 Technical Report.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference DeepSeek-V3 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:00.038860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b7360b8-110d-47b9-a140-000b9b0cab85 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:00.133693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9117e012-3f1c-47d6-9b79-58783242eea5 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:05.128766Z

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 4d96180c-7e34-4588-b55a-2bb8ac645924 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:04.945624Z

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 39d47bc8-9f11-4b4f-a4d5-29fc19b45eb6 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:04.729592Z

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 c9d52bb4-15be-4955-bc9d-3d23740d9950 · outbound

This paper cites SparQ Attention: Bandwidth-Efficient LLM Inference.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference SparQ Attention: Bandwidth-Efficient LLM Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:00.637951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e03dd71-908c-4e4f-a12d-e05dcd4523fe · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:00.727994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db9cac96-1645-4357-b4db-31300544deb0 · outbound

This paper cites Loki: Low-rank Keys for Efficient Sparse Attention.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Loki: Low-rank Keys for Efficient Sparse Attention

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:00.797982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2178ee9d-6c7e-4b91-bb98-be1e9a5b5e6b · outbound

This paper cites ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:00.895653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1537f08e-129f-4807-ac9a-fcca9ebf512d · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:04.503621Z

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 f8c98f77-f5ad-4674-bfef-2c7c10eb8831 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:01.145607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42e625ea-5c24-45e6-899b-70ef97c44005 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:01.299814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d50ea01c-306d-4f00-ad0e-a8fda0e12902 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:04.278953Z

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 266518e8-ac32-4b3a-aa97-26293bc11f2a · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:04.091956Z

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 e3fd5a6e-c4bc-4898-9132-2d7c822408d2 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:03.842301Z

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 536b9b5a-dd44-432e-93ed-2e855ea981e6 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:03.625450Z

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 aa457d13-4aa4-42e0-b74b-cda988a847f4 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Efficient Streaming Language Models with Attention Sinks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:01.762361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8438d211-1c14-4880-88be-6b85ebcf3437 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:01.860825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 823f57db-0166-4562-9bd7-c85d58cb7e38 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:03.351191Z

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 99128bbc-79ff-452d-8e15-744b868cf3bf · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:03.056187Z

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 06830067-bf8d-4a76-ac42-edd18430f3f6 · outbound

This paper cites an unresolved cited work.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:26:02.786954Z

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 baecab88-b21b-4b40-ab88-44eae0a1654e · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference SGLang: Efficient Execution of Structured Language Model Programs

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:02.274620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8a1c847a-d352-4183-97c4-ee08663a825b · inbound

Training-Free Hashing-Based Attention via Binary Principal Components cites this paper.

Training-Free Hashing-Based Attention via Binary Principal Components HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:45:48.754100Z

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.