Paper Citation Record · LEDGER

Inference-time sparse attention with asymmetric indexing

As of 8 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 4 inbound Pith citation observations for arXiv:2502.08246.

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

pith.paper-citation-record.v1
2502.08246 v2

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T05:56:55.205911Z

measured 33 of 33 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:30:34.307068Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T06:26:27.473700Z

Reference resolution

29 of 29 outbound references displayed

verified exact1
verified fuzzy6
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 07dff465-6a1d-475b-b7c1-595a1fb78750 · outbound

This paper cites FrameQuant: Flexible Low-Bit Quantization for Transformers.

Inference-time sparse attention with asymmetric indexing FrameQuant: Flexible Low-Bit Quantization for Transformers

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.058667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67d35da-1b5b-415a-8202-fdc7447fb3e4 · outbound

This paper cites The Llama 3 Herd of Models.

Inference-time sparse attention with asymmetric indexing The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.097815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a9ccc8-b0d2-472b-9a6d-516d0b0bc9bb · outbound

This paper cites HyperAttention: Long-context Attention in Near-Linear Time.

Inference-time sparse attention with asymmetric indexing HyperAttention: Long-context Attention in Near-Linear Time

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.108746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae5d067-cf72-4d99-8dbe-5217f50746ea · outbound

This paper cites Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

Inference-time sparse attention with asymmetric indexing Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.114423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d3def96-2c07-4025-8407-26f66ab15109 · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

Inference-time sparse attention with asymmetric indexing GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.130242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52d670ad-7df4-43db-8848-d81d2bf2fceb · outbound

This paper cites Reformer: The Efficient Transformer.

Inference-time sparse attention with asymmetric indexing Reformer: The Efficient Transformer

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.135227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f87da6-4f86-4c26-898f-2b6ad05b7a0b · outbound

This paper cites Cagra: Highly parallel graph construc- 9 tion and approximate nearest neighbor search for gpus.

Inference-time sparse attention with asymmetric indexing Cagra: Highly parallel graph construc- 9 tion and approximate nearest neighbor search for gpus

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:56:55.726260Z

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.

Observation 6ead6b36-324d-4e29-adee-57887e3ebe89 · outbound

This paper cites Improving regularized singular value decom- position for collaborative filtering.

Inference-time sparse attention with asymmetric indexing Improving regularized singular value decom- position for collaborative filtering

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:56:55.709797Z

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.

Observation 8f22ad8a-55cf-4403-ae56-74e0b55c3d61 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

Inference-time sparse attention with asymmetric indexing Compressive Transformers for Long-Range Sequence Modelling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.160423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a58cc39-dc3f-4447-a71d-14b5c9ba66dd · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

Inference-time sparse attention with asymmetric indexing FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.165619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b6c9067-deb7-41ba-aab3-d2b37d61a8a3 · outbound

This paper cites Results of the Big ANN: NeurIPS'23 competition.

Inference-time sparse attention with asymmetric indexing Results of the Big ANN: NeurIPS'23 competition

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.170777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 957e5b3b-3e0f-4ac3-9c16-2bf706c27f9f · outbound

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

Inference-time sparse attention with asymmetric indexing Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.176049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b36221c6-b8e9-4290-ae1a-ac94fbaaae00 · outbound

This paper cites Memory Mosaics.

Inference-time sparse attention with asymmetric indexing Memory Mosaics

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.181350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 880b302c-31ea-4bae-ac32-f47341b6bd03 · outbound

This paper cites Appendix A pro- vides details regarding the training procedure.

Inference-time sparse attention with asymmetric indexing Appendix A pro- vides details regarding the training procedure

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:56:55.692959Z

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.

Observation bf00e82f-bebe-4867-8ca2-e55be2557d8e · outbound

This paper cites an unresolved cited work.

Inference-time sparse attention with asymmetric indexing Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-08T05:56:55.659412Z

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.

Observation f587cec1-80df-40f6-baa4-a41073328b53 · outbound

This paper cites selectivity for three LSH variants, compared to a random selection and a partition based on k-means (the baseline forSaap), on 4 representative heads.

Inference-time sparse attention with asymmetric indexing selectivity for three LSH variants, compared to a random selection and a partition based on k-means (the baseline forSaap), on 4 representative heads

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:56:55.627616Z

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.

Observation b27fd103-0123-4524-b3c6-4b94fc8848a0 · outbound

This paper cites Q-model short-range.

Inference-time sparse attention with asymmetric indexing Q-model short-range

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:56:55.643796Z

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.

Observation 7ab0b21a-dc05-4bdb-a7a9-b5a3fe17e800 · outbound

This paper cites The vector search relies on collisions between the buckets: a key is considered only if it is hashed together with the query in at least two hash tables.

Inference-time sparse attention with asymmetric indexing The vector search relies on collisions between the buckets: a key is considered only if it is hashed together with the query in at least two hash tables

Reference 200

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:56:55.676201Z

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.

Observation fd2966b4-0405-4e31-8e01-e223895c1542 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Inference-time sparse attention with asymmetric indexing BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.081609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa5d188f-de7d-4b6b-aa76-4402a1476d37 · outbound

This paper cites YaRN: Efficient Context Window Extension of Large Language Models.

Inference-time sparse attention with asymmetric indexing YaRN: Efficient Context Window Extension of Large Language Models

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.155299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f49897ef-7688-4d8c-b9ef-022941e30786 · outbound

This paper cites Learning Space Partitions for Nearest Neighbor Search.

Inference-time sparse attention with asymmetric indexing Learning Space Partitions for Nearest Neighbor Search

Reference 2011

Resolution: verified exact; local_arxiv, observed 2026-08-08T05:56:55.528000Z

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.

Observation c3d0a53a-70c3-43a8-b47b-2fab036689a1 · outbound

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

Inference-time sparse attention with asymmetric indexing RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.119683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04bebca2-fadd-4861-85d6-2318b7ea14c0 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

Inference-time sparse attention with asymmetric indexing Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.103328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca8c305b-3815-450c-b9de-c8e2612b4d7c · outbound

This paper cites OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queries.

Inference-time sparse attention with asymmetric indexing OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queries

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.124568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f6969a0-7d36-472b-8b0c-b0c42d4ca5e8 · outbound

This paper cites The Faiss library.

Inference-time sparse attention with asymmetric indexing The Faiss library

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.092546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434c7a4e-1764-49e0-a228-6388ec9b18d4 · outbound

This paper cites RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search.

Inference-time sparse attention with asymmetric indexing RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.076094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2a28fcf-820d-414d-baf0-d4d999d9731b · outbound

This paper cites Evaluating Quantized Large Language Models.

Inference-time sparse attention with asymmetric indexing Evaluating Quantized Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.140233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 363f83c3-97ca-4007-9339-510daa08ff7d · outbound

This paper cites Language Models are Few-Shot Learners.

Inference-time sparse attention with asymmetric indexing Language Models are Few-Shot Learners

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.070660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afbf3ce5-af35-4ce4-afb4-183f17ebfceb · outbound

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

Inference-time sparse attention with asymmetric indexing GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.064747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 327fddec-e36e-4899-b590-8eb377646723 · inbound

Kinetics: Rethinking Test-Time Scaling Laws cites this paper.

Kinetics: Rethinking Test-Time Scaling Laws Inference-time sparse attention with asymmetric indexing

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:30:34.307068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a362d9b-f617-41b7-bbf1-6fb73bd032fe · inbound

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

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning Inference-time sparse attention with asymmetric indexing

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:06:32.671170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e9aa857-0624-49f5-97cb-93f7d82b8e16 · inbound

ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation cites this paper.

ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation Inference-time sparse attention with asymmetric indexing

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:26:27.475026Z

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.

Observation c0e25e1c-d8e2-4586-bc1b-de89745c62a9 · inbound

Cluster with Auctions for Vector Search cites this paper.

Cluster with Auctions for Vector Search Inference-time sparse attention with asymmetric indexing

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-02T04:16:16.178633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.