Paper Citation Record · LEDGER

Rectified Sparse Attention

As of 19 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 4 inbound Pith citation observations for arXiv:2506.04108.

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

pith.paper-citation-record.v1
2506.04108 v2

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:52:48.987113Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:06:32.693476Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T13:46:58.816966Z

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy2
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 195f9a5b-f13b-4520-a5d3-b22ff14f473a · outbound

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

Rectified Sparse Attention SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.200672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbacd52a-ac00-421f-b26f-472ea2bbf55b · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Rectified Sparse Attention GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.285123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16245e3d-3417-44ff-8c73-564e3e612f0b · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

Rectified Sparse Attention Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.349290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d71bcdd-d3e0-46c7-98e1-921e2eea93a6 · outbound

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

Rectified Sparse Attention MagicPIG: LSH Sampling for Efficient LLM Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.465707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca1098b-5ddc-474f-a14e-ce7f8b4b2dfa · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Rectified Sparse Attention Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.527304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed759aec-6814-40db-a56d-41151166bdf9 · outbound

This paper cites Flash-Decoding for long-context inference.https://crfm.stanford.edu/2023/10/12/flashdecoding.html, 2023.

Rectified Sparse Attention Flash-Decoding for long-context inference.https://crfm.stanford.edu/2023/10/12/flashdecoding.html, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:49.268981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22abf7b4-91e0-48e1-b5b4-8b0ae3a4152c · outbound

This paper cites MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models.

Rectified Sparse Attention MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.650576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e892edf0-045c-41f9-81e0-73dd74f82b7f · outbound

This paper cites SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs.

Rectified Sparse Attention SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.764869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99217db7-9ac4-4fd3-91b0-9f5e57ab2e5c · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Rectified Sparse Attention DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.868706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8639a1-dc19-4f1b-8861-83e1711016ae · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

Rectified Sparse Attention OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.901428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c5d9b4-69ab-498a-9051-24b27898a446 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Rectified Sparse Attention Measuring mathematical problem solving with the math dataset

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.935265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17c4b2d3-7d80-4f7e-a321-478c29739989 · outbound

This paper cites DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference.

Rectified Sparse Attention DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.938385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12ea0f1f-3189-47b6-864f-d1ea47ef7f87 · outbound

This paper cites OpenAI o1 System Card.

Rectified Sparse Attention OpenAI o1 System Card

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.941415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35a5dac5-0e4d-46d9-b136-1aecd9c73860 · outbound

This paper cites Fast inference from transformers via speculative decoding.

Rectified Sparse Attention Fast inference from transformers via speculative decoding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.944325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be024e36-8e0f-44cc-909d-dd3b550312c7 · outbound

This paper cites Solving quantitative reasoning problems with language models.Advances in Neural Information Processing Systems, 35:3843–3857, 2022.

Rectified Sparse Attention Solving quantitative reasoning problems with language models.Advances in Neural Information Processing Systems, 35:3843–3857, 2022

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.947196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11fa7331-4345-4ad5-ac3d-8fe859d827c4 · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

Rectified Sparse Attention EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.949963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec6e455-732c-44d0-b336-17cb5fc7c4e6 · outbound

This paper cites MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline.

Rectified Sparse Attention MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.952928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b1cfc7-6b65-4532-a222-6d99636ed20f · outbound

This paper cites ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression.

Rectified Sparse Attention ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.956989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131d3691-37ae-43d6-81b2-a7d6ccfa2d99 · outbound

This paper cites MoBA: Mixture of Block Attention for Long-Context LLMs.

Rectified Sparse Attention MoBA: Mixture of Block Attention for Long-Context LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.960314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff56fa26-426a-4638-807d-425e491602f4 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Rectified Sparse Attention Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.963403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9161153-b987-4d15-aee1-1ea702c8f66c · outbound

This paper cites MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding.

Rectified Sparse Attention MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.966152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee44efbc-ac4b-45df-b458-0d636cf0ee21 · outbound

This paper cites TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding.

Rectified Sparse Attention TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.969030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e5d68fd-4e9c-4eae-8d71-39bf16189b3d · outbound

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

Rectified Sparse Attention Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.972268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a8181b3-5ed7-4a97-975b-447725659275 · outbound

This paper cites InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory.

Rectified Sparse Attention InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.975137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 524b4230-df1a-4c66-a691-39c2f3aa839b · outbound

This paper cites Qwen2.5 Technical Report.

Rectified Sparse Attention Qwen2.5 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.978094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb1e160-cf1b-40f4-8c89-1d923ac34cf3 · outbound

This paper cites Qwen2.5-1M Technical Report.

Rectified Sparse Attention Qwen2.5-1M Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.981099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9a5af27-b368-4d42-817a-6675be5981b5 · outbound

This paper cites Orca: A distributed serving system for Transformer-based generative models.

Rectified Sparse Attention Orca: A distributed serving system for Transformer-based generative models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:49.239761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cb718aeb-3183-4d09-8cca-503448e3a0ba · outbound

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

Rectified Sparse Attention Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.987113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 973f0b67-f390-49b2-b41c-433cfb715649 · inbound

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

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning Rectified Sparse Attention

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:06:32.693476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fd29474-9a0f-4b7a-89b8-11bf887c5093 · inbound

Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants cites this paper.

Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants Rectified Sparse Attention

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T11:41:30.042725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cf2a2230-520c-4f33-b5b1-5d835d2570f9 · inbound

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

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding Rectified Sparse Attention

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:21:18.626267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5361cd55-4d42-455c-8d9c-b0a2d1a68d7f · inbound

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing cites this paper.

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing Rectified Sparse Attention

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:46:58.818402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.