Paper Citation Record · LEDGER

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 36 inbound Pith citation observations for arXiv:2502.20766.

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

pith.paper-citation-record.v1
2502.20766 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 36 of 36 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 36 of 36 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T11:11:17.702371Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 730aa723-d591-417c-832f-5400fda1cef9 · inbound

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation cites this paper.

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T11:11:17.702371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e55e330-e88d-4e8e-bf2a-f6e8cf2c29fa · inbound

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity cites this paper.

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:50:53.833323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bfbc421-98c1-467d-a47e-8c7bdcfe314a · inbound

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers cites this paper.

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:15.864790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94ff5f04-9d57-4434-b600-a547ef219e7c · inbound

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning cites this paper.

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:06:32.635500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17a278f5-ba27-41f6-b918-962f6bd530f4 · inbound

Lag-Relative Sparse Attention In Long Context Training cites this paper.

Lag-Relative Sparse Attention In Long Context Training FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:10:46.279283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da99d513-7753-4c4a-9aec-2bf4bf27ee7d · inbound

Sparse Fine-Tuning of Transformers for Generative Tasks cites this paper.

Sparse Fine-Tuning of Transformers for Generative Tasks FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:30:14.855194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4be6df4-9618-4fd4-9dac-81eac982d980 · inbound

DeltaLLM: A Training-Free Framework Exploiting Temporal Sparsity for Efficient Edge LLM Inference cites this paper.

DeltaLLM: A Training-Free Framework Exploiting Temporal Sparsity for Efficient Edge LLM Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:44.573805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe522093-4b58-4108-9d8d-c7eacb0b20b3 · inbound

Accelerating Prefilling via Decoding-time Contribution Sparsity cites this paper.

Accelerating Prefilling via Decoding-time Contribution Sparsity FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-19T03:06:59.904965Z

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 b099f32b-71b1-4685-95ba-b605fdd08fd1 · inbound

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference cites this paper.

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-18T22:06:52.158913Z

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 041c5d06-2132-4dee-89d7-aaed139c5a31 · inbound

UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention cites this paper.

UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T09:20:06.613749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1efe3e05-b733-407c-9421-0bd925bc76f0 · inbound

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding cites this paper.

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:21:18.631790Z

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 a8ba8449-c17d-4dc4-b904-6eca1fe3294d · inbound

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs cites this paper.

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T03:37:50.122140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab1a122-93ed-4304-8588-665627252c4a · inbound

Prism: Spectral-Aware Block-Sparse Attention cites this paper.

Prism: Spectral-Aware Block-Sparse Attention FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:22:54.033487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4097eb8f-ba2f-4c77-b234-586b7e982609 · inbound

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference cites this paper.

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:00:17.890303Z

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 7d49031b-1479-480a-9a3c-491dd2765964 · inbound

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference cites this paper.

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:50:09.505344Z

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 a7b82960-56e5-44b9-8d0e-709c3268313c · inbound

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference cites this paper.

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T22:05:43.018334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40daa6a6-231c-4877-b494-10baa294ce7a · inbound

Stem: Rethinking Causal Information Flow in Sparse Attention cites this paper.

Stem: Rethinking Causal Information Flow in Sparse Attention FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T02:39:28.798730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70435810-0bee-42cc-8d50-8281bf98cce0 · inbound

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding cites this paper.

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:11:18.913894Z

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 956182f1-e1bb-406d-b559-7b64a421254f · inbound

Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache cites this paper.

Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-11T01:15:50.421216Z

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 96c16d51-7e17-4785-b372-5c58b88a422f · inbound

An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference cites this paper.

An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.249978Z

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 5f47c392-359e-47ba-872e-b937bd6e455c · inbound

ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing cites this paper.

ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:26:30.101043Z

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 691d2615-4b55-4092-9f23-e629ebced8cf · inbound

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection cites this paper.

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-19T21:22:47.999879Z

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 9df60470-ba16-4bd9-9fa3-769b49d555f1 · inbound

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference cites this paper.

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:18:13.988453Z

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 45c82e97-281a-475d-9fd9-670ff0b15d49 · inbound

SSV: Sparse Speculative Verification for Efficient LLM Inference cites this paper.

SSV: Sparse Speculative Verification for Efficient LLM Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:14:45.989128Z

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 d00311f8-5d3e-4a4d-9470-d7e43812f682 · inbound

PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models cites this paper.

PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T05:09:38.711780Z

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 c47c37df-1e68-4dfd-8707-18e5f507d54d · inbound

DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation cites this paper.

DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:45:20.108521Z

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 132123ff-4f1b-4575-9f2d-4375c6e787aa · inbound

SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance cites this paper.

SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:37:31.238420Z

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 52f26710-85f6-4606-9141-17a1b7facdf3 · inbound

Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models cites this paper.

Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:57:38.696659Z

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 34acb13f-32eb-42b8-ac10-087a2646c71b · inbound

LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval cites this paper.

LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T10:34:36.227719Z

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 d930d33b-b247-4e1f-8498-963cfe56059b · inbound

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers cites this paper.

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T01:12:13.747675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04cc3de6-669c-4141-a719-37c79c982594 · inbound

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers cites this paper.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.951687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2f80cf7-bab2-4401-ada4-f300e1b68339 · inbound

Dropping the Anchor: Statistical Context Summarization for Distributed Systems via Pulsar Attention cites this paper.

Dropping the Anchor: Statistical Context Summarization for Distributed Systems via Pulsar Attention FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T14:02:40.838142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 615534be-7122-4418-8206-4f466bc122a5 · inbound

PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention cites this paper.

PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T11:04:04.526969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba7fe839-b193-4471-a8cc-6705ae71df6c · inbound

CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention cites this paper.

CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T02:55:46.301880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0380e261-edaa-46d6-8086-6632893ec8f6 · inbound

SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference cites this paper.

SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T20:50:03.984247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6083fe37-9c5f-40e6-97e3-d61f110a605a · inbound

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding cites this paper.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.360123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.