Pith. sign in

Paper Citation Record · LEDGER

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing

As of 8 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2608.01662.

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

pith.paper-citation-record.v1
2608.01662 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:15:02.874621Z

measured 44 of 44 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

44 of 44 outbound references displayed

  • verified exact0
  • verified fuzzy6
  • unresolved38
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e1b16cfd-495f-47ae-8111-e925a19ad3bf · outbound

This paper cites Scaling embeddings outperforms scaling experts in language models.arXiv preprint arXiv:2601.21204,.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Scaling embeddings outperforms scaling experts in language models.arXiv preprint arXiv:2601.21204,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.740078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.740078Z digest=sha256:437f7752ddb742a6f0e88a52afe2fa708975807504b1db061fe3ac5be7b13728

Observation 6f8f5671-8f20-460f-98a7-5b85b9dd86b4 · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Generating Long Sequences with Sparse Transformers

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.821069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.821069Z digest=sha256:12e0983f7bdd0fc8bb03b37993d0f3855af3584b61e98e6950f54641effbdd6e

Observation 9f1fa715-f51c-46d8-86f0-3e8c51e1ed6a · outbound

This paper cites One of the special magic uuids for <key> is: <value>.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing One of the special magic uuids for <key> is: <value>

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T00:15:04.590583Z

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=2026-08-07T00:15:02.764834Z digest=sha256:ce4049bbf2b32e1658eb8a49f65b319483213b92156d9c24793cc36a90a2b6c1

Observation 702f69cd-b4d2-4895-a7fb-9a0f6c7b9e49 · outbound

This paper cites Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.076452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.076452Z digest=sha256:97528b00c5d9d5cbb3d73ab2746989b1a5e96a26faee8445d304393f4b8fbbbb

Observation 52174d3d-a955-4b17-a3e3-1002ef8862be · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Fast Transformer Decoding: One Write-Head is All You Need

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.118390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.118390Z digest=sha256:b2508f51345dadc0413abdb91a9a927ca4c7afe2f0e03d206e12f4d14e317b54

Observation 53c7ab1a-1668-480a-bfff-c9e4380598e3 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.222968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.222968Z digest=sha256:ae1f3365bbbffaadedc3ad5efce4f49ef636d35b78395355bf1987d657d46022

Observation 7b91b98f-a8c3-4b7c-8d0c-8572c21d73d5 · outbound

This paper cites Longcat-flash technical report.arXiv preprint arXiv:2509.01322,.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Longcat-flash technical report.arXiv preprint arXiv:2509.01322,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.328533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.328533Z digest=sha256:ee7aaf4b793d80716b7bd3ad3dd50fd7f5d888ddad3c47ad49f9acadab8b8bfc

Observation 019db5bc-56a4-48fb-9fa3-b57f9cde2e96 · outbound

This paper cites Indexcache: Accelerating sparse attention via cross-layer index reuse.arXiv preprint arXiv:2603.12201,.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Indexcache: Accelerating sparse attention via cross-layer index reuse.arXiv preprint arXiv:2603.12201,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.418924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.418924Z digest=sha256:a4f9456fad3e1d9dd2347c698c017c4b2918e48b8ae5ad7666a35df91a6dcaf0

Observation 45d857b8-dd7b-4310-abb1-374c8be88b12 · outbound

This paper cites HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.494998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.494998Z digest=sha256:cc9c2c3e08588d7ba7c2331c192ec2ec031af5fb1f626c0d03913a13b40723e5

Observation e15616c0-be7d-4e78-958d-11423f95cb42 · outbound

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

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.585567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.585567Z digest=sha256:7ee58e6dda4a99cbfd34a619948720a88fa6fd5300473dde411742cc03693051

Observation 116aabc7-a463-4806-b8cb-df4a68baae96 · outbound

This paper cites Cohen, Ruslan Salakhutdinov, and Christopher D.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Cohen, Ruslan Salakhutdinov, and Christopher D

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T00:15:05.768803Z

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=2026-08-07T00:15:00.655639Z digest=sha256:2738e9b007ecce526e8c33de0bfd78afd69c7e7ce277f1401ac4f80ed6d863bd

Observation 034893be-4464-47b1-933e-19a3fabebe93 · outbound

This paper cites $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.919480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.919480Z digest=sha256:b1a4d71ab7187e9f7e8488650c732b6fa0d49a3a7f06adf5f470abb05147cc06

Observation 6bb453d7-773a-4300-8d67-f6e1d6d0323c · outbound

This paper cites Enabling large language models to generate text with citations.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Enabling large language models to generate text with citations

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T00:15:05.633879Z

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=2026-08-07T00:15:00.987295Z digest=sha256:cc084229a6357d8c870cec47c1ec1734f9f03638f4eeb7e5b5845cc681859503

Observation 37de51b9-967c-436a-afda-c6f2fb7760ed · outbound

This paper cites ASQA: Factoid questions meet long-form answers.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing ASQA: Factoid questions meet long-form answers

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T00:15:05.385070Z

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=2026-08-07T00:15:01.092372Z digest=sha256:9243beec96ed5d1556dc33ef1aedbe4d9e2eca28fe165beb3a01b45757eb53a4

Observation ad97260d-dd9f-40ee-909f-7c7ebfd7fc85 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.342992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.342992Z digest=sha256:f3f8f2ea1e9f787c657ff391c141486e3bc0fcaef45d03e9eca3570f4decf278

Observation 6fb0e280-080f-4f24-91ae-fef0dd6292ac · outbound

This paper cites CMMLU: Measuring massive multitask language understanding in Chinese.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing CMMLU: Measuring massive multitask language understanding in Chinese

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.418782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.418782Z digest=sha256:79ac685c7fbc702458d71f46fad05506b705a37ae7b2ca4994ebe50c92603954

Observation 9ae670a3-6f2b-498e-ba8e-fdf8b528eb38 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.496864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.496864Z digest=sha256:ebcf31e7f99b300d0dac4d3706a830d5178bdde6f9c1a769b58b999e00c977ff

Observation aab2b90d-3835-4ec9-afc4-15db884d2536 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.Advances in Neural Information Processing Systems, 34, 2021b.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Measuring mathematical problem solving with the math dataset.Advances in Neural Information Processing Systems, 34, 2021b

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T00:15:05.208704Z

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=2026-08-07T00:15:01.584498Z digest=sha256:2d8eca48975a92aa714c109389b2df212750523e3599ff53594bced866b37a40

Observation d1ac78a3-4284-4036-a7a3-9121c2e7db91 · outbound

This paper cites an unresolved cited work.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Unresolved cited work

Reference 27

Resolution
unresolved
raw_fallback, observed 2026-08-07T00:15:04.942080Z

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=2026-08-07T00:15:01.634284Z digest=sha256:6d44854fbe3fcf2eb09e812492d1d9afe973764730251bcad59a6e783f9b4033

Observation 89ce7e4c-62bd-46d9-86ab-d0bc1bfe1dfb · outbound

This paper cites Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.703012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.703012Z digest=sha256:3271fe594271ad7bb30349adf1d8c515ebe118aed259d045fc9401f8ff4a10b2

Observation a8724515-b994-4f3f-a9a1-6f2b7596e9a0 · outbound

This paper cites AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.779702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.779702Z digest=sha256:ceec95aabf532bfdb2de8b42777018cce99d6c894493df01c93ceab6e71641c3

Observation d6c7b396-b7b6-4d76-8830-121b22e8f1e1 · outbound

This paper cites HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.857982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.857982Z digest=sha256:c52473a6ba6a3d6a859cdc3bcc7cf4692aeac3723bab9437f641bffd2d0e1773

Observation 2ed5ceb0-acee-491e-9940-a6d3237859b4 · outbound

This paper cites Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.929996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.929996Z digest=sha256:c1bb29ca41bfce18e8459759c7eec76e95da82daf8eaba3cd258c1fd4a206c50

Observation bc8f1e5e-5aa6-4b3b-a87e-5cbc7e94edbd · outbound

This paper cites Cheng Jiayang, Dongyu Ru, Lin Qiu, Yiyang Li, Xuezhi Cao, Yangqiu Song, and Xunliang Cai.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Cheng Jiayang, Dongyu Ru, Lin Qiu, Yiyang Li, Xuezhi Cao, Yangqiu Song, and Xunliang Cai

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.007202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.007202Z digest=sha256:8a163d3e9700beae6a5ee9bd929ecda8e3c01e1196e0ac55d57942584a9f5e90

Observation 427bbb7b-92a0-4ff2-bb27-bd2d1a2524a0 · outbound

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

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.090937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.090937Z digest=sha256:3168b15ab96be982a02c76331370dac2cffeb7003ee35bf857f5473cca828301

Observation e5d09d34-2f96-49dd-a02f-a9263fbbb5b8 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.128091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.128091Z digest=sha256:4e93980c4bb8c968ca1b9763a656461fd3db6a5710abce003d2db1f8da81d92e

Observation 7c01f29e-c24b-40ea-a17f-a42ef4a6ad91 · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.225669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.225669Z digest=sha256:72edd593edf95ca88eb0564f766dc0d80afcce17e0f34e9435c3fb1d2099b7d3

Observation 014ed2bc-3ade-4a71-affb-af5bca762b91 · outbound

This paper cites Vitabench: Benchmarking llm agents with versatile interactive tasks in real-world applications.arXiv preprint arXiv:2509.26490,.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Vitabench: Benchmarking llm agents with versatile interactive tasks in real-world applications.arXiv preprint arXiv:2509.26490,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.315050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.315050Z digest=sha256:04d9b5fe93d93c35c08e4b72b04a39266ebd3d77754d66d08ce2e18a6c69ff8c

Observation 4fd26b7b-4fd4-490e-9d77-bc009b77875f · outbound

This paper cites MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.375041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.375041Z digest=sha256:ab03301bdb2a7aa9018b1aa8cd91faef0d57eac0d4ddd17dda6843a104132b21

Observation f46e8191-304f-4154-8c4a-13cca91cfb61 · outbound

This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.431765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.431765Z digest=sha256:3c897f4489bb8aa6bd5405d3255448b49f045dddcba80a5398d6b7c9dad24c51

Observation d669be28-84fc-4462-a3aa-052568ebd904 · outbound

This paper cites BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.528644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.528644Z digest=sha256:1db47207063aa3c189f5c09f61a2b9ca0c4853a46b97070f14b522b1eba7dd3f

Observation 9a0af43d-746a-40c8-beb3-10651fa3be50 · outbound

This paper cites Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.576660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.576660Z digest=sha256:e4b38d0127482e99c4e1f4473bebfcc709a032dbf104a24fe5b32a1156abb30c

Observation 80e6a748-7ed9-4e3f-9a43-44d6fa8b8ae6 · outbound

This paper cites Thang Luong, Dawsen Hwang, Hoang H.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Thang Luong, Dawsen Hwang, Hoang H

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.634076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.634076Z digest=sha256:3ed5653b45f29b61bf4517d2a240e15aa9cfb84df6094179c43561168cd3f558

Observation 8e8006e7-7c29-4490-af12-2a17a25342f9 · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026b.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026b

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:02.707257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:02.707257Z digest=sha256:65d0776ab21ae2fcfcd80f47cb49e7ef3e3c1dd4fbe538fe762af8234e9c93c9

Observation 19fdecd0-0e38-4f60-b8b4-a7ad35186fba · outbound

This paper cites Red brackets above the panel mark the key spans of the task description, the target needle line, and the question.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Red brackets above the panel mark the key spans of the task description, the target needle line, and the question

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T00:15:04.366279Z

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=2026-08-07T00:15:02.874621Z digest=sha256:775cae02c66b802618b229a14b310e07a3e6f018667a5384f0dd140af8f812e8

Observation fce5bcf1-6e49-4ab0-ad0a-908332969ef0 · outbound

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

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.459331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.459331Z digest=sha256:14a5dd85a12e31adcbe39b041821764fa20eef42e7cea63729deee8e44595d77

Observation c3824aab-212a-482c-a549-0be5e1929db6 · outbound

This paper cites Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.729438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.729438Z digest=sha256:9acec4cd58de177baa2e0ea1e27f22f3ac39a12ce2e03a5d9798e073f89751d5

Observation e8e1752c-f6c3-410d-9468-9b32abe58f70 · outbound

This paper cites Longformer: The Long-Document Transformer.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Longformer: The Long-Document Transformer

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.924306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.924306Z digest=sha256:130f84561ec0a8ea45e5328ccb63e3fed01c25c253bac2c3281d0e05d3a618a7

Observation ff9eec77-1f0e-424b-9000-182e34b6c7e1 · outbound

This paper cites RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.004201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.004201Z digest=sha256:dee33b358cdd1eda02b5d890af1c855a23c1dcd5f026ddf5274cac3322d3b569

Observation 7a2944d4-1814-4f02-a2b4-eb33477158ee · outbound

This paper cites QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:01.204848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:01.204848Z digest=sha256:64f0853626ab8ba4b51b84a441bc562e317a2fbef52617fd84fd8e4318856aae

Observation 0b53029e-a9eb-449b-b508-10b3b683e6de · outbound

This paper cites MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-07T00:15:00.827604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:15:00.827604Z digest=sha256:8a91f3934735d09c524d4390f18c9cba9e8ec0923b9f2d2b3a54642a16051eca

Observation 6b24c3ed-7829-4d9e-a88d-375cfbc9cf66 · outbound

This paper cites Kascade: A practical sparse attention method for long-context llm inference.arXiv preprint arXiv:2512.16391,.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Kascade: A practical sparse attention method for long-context llm inference.arXiv preprint arXiv:2512.16391,

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.569127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.569127Z digest=sha256:7f2362c6ce8fdd024a82fc1f99cf11043bba3961f22c384ab5b697d954a2f4ed

Observation 9ea74bb0-fcd8-4fca-9397-4a1c932b3050 · outbound

This paper cites Hysparse: A hybrid sparse attention architecture with oracle token selection and kv cache sharing.

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing Hysparse: A hybrid sparse attention architecture with oracle token selection and kv cache sharing

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.656661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.656661Z digest=sha256:73d8234ff50b459cfb6487cfe5b12673c7bc88e8722b58bc678f406c21bbcadd

Observation 7b393277-590e-4e98-87c1-1ddf4dbe816e · outbound

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

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 2026

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:59.516777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:59.516777Z digest=sha256:c3536e9184fefe5465a5f424ff6dcd94ff34cfc3e7c5935fb1fbcee1643c417f

Pith citing papers

No inbound Pith citation observations are available.