Paper Citation Record · LEDGER

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

As of 19 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 10 inbound Pith citation observations for arXiv:2506.09092.

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

pith.paper-citation-record.v1
2506.09092 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:10:31.549722Z

measured 22 of 22 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 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:15:01.845918Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

12 of 12 outbound references displayed

verified exact0
verified fuzzy9
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation fa118d5e-b838-444c-ade4-df7a3cd421b2 · outbound

This paper cites Amazon codewhisperer: Ai coding companion, 2023.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Amazon codewhisperer: Ai coding companion, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.682774Z

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 c330894e-54af-4c28-abf1-9c1fbc2940f9 · outbound

This paper cites Claude 3 model family, 2024.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Claude 3 model family, 2024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.673798Z

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 a78bea63-4f38-4e56-84cd-ea71e45ec470 · outbound

This paper cites CUDA Pro- gramming: A Developer’s Guide to Parallel Computing with GPUs, 2012.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels CUDA Pro- gramming: A Developer’s Guide to Parallel Computing with GPUs, 2012

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.663959Z

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 45eff9ad-67a1-41be-8f46-7881882a8119 · outbound

This paper cites DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:31.519990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d84d7ef-71e0-47b3-8928-4a009087270e · outbound

This paper cites The ai cuda engineer: Agentic cuda kernel discovery, optimization and composition.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels The ai cuda engineer: Agentic cuda kernel discovery, optimization and composition

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.652539Z

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 de34a35f-effd-47c2-a018-7f6954fa172f · outbound

This paper cites Challenges.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Challenges

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.641966Z

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 f4ae6588-1644-4a7b-83ff-a10121c555e7 · outbound

This paper cites DeepSeek-V3 Technical Report.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels DeepSeek-V3 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:31.531710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9fc56e2-a262-47ef-949e-ffa2235fe472 · outbound

This paper cites Cuda code samples.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Cuda code samples

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.631428Z

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 c5387505-3e2f-4f78-8f11-ab5d903d01a9 · outbound

This paper cites KernelBench: Can LLMs Write Efficient GPU Kernels?.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels KernelBench: Can LLMs Write Efficient GPU Kernels?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:31.539023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f71c777-54da-4836-9a26-aeefb0b6fa6c · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.621300Z

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 fb8ca65c-bdc4-4939-9a4a-1cfdbd6318dd · outbound

This paper cites Code llama: Open foundation models for code, 2023.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Code llama: Open foundation models for code, 2023

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.610972Z

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 91d9cfcb-0a3c-454e-bc1f-019bf10ab1e4 · outbound

This paper cites Addison-Wesley Professional, 2010.

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels Addison-Wesley Professional, 2010

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:31.600473Z

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.

Pith citing papers

Observation e71d3a3a-65b9-438e-82b5-90029ae6c159 · inbound

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning cites this paper.

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:15:01.845918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37216c29-8483-4173-95b2-5bb53bb56ec8 · inbound

Towards Automated Kernel Generation in the Era of LLMs cites this paper.

Towards Automated Kernel Generation in the Era of LLMs CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T08:49:46.409983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21201f5c-95b4-4d0f-9748-9ed0eb2ba1c2 · inbound

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs cites this paper.

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:23:07.105062Z

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 aeb43cf3-2da9-4522-b2c9-8ad6fa572a1c · inbound

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs cites this paper.

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:24:02.573383Z

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 2f9d17e0-d227-4bca-ac2c-620478739db1 · inbound

HTAM: Hierarchical Transition-Attended Memory for Operator Optimization cites this paper.

HTAM: Hierarchical Transition-Attended Memory for Operator Optimization CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:33:14.089027Z

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 860bb8a5-01d8-4a17-be26-fe58777bcdd6 · inbound

KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators cites this paper.

KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:46:19.676756Z

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 b98419fc-2385-4666-a182-b26eb372c941 · inbound

LLM-Based Porting of Optimized C++ to CUDA Through Deoptimization and Reoptimization cites this paper.

LLM-Based Porting of Optimized C++ to CUDA Through Deoptimization and Reoptimization CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:37:06.701498Z

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 668b9fe4-1d4d-47fe-bebd-3888ad8f4865 · inbound

Generated, Parallel, Scalable? A Study of Agentic AI-Generated Julia Code on Supercomputers cites this paper.

Generated, Parallel, Scalable? A Study of Agentic AI-Generated Julia Code on Supercomputers CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-06-27T03:10:24.930243Z

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 e4aaab62-31f2-4e11-834a-be2f035cea00 · inbound

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation cites this paper.

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:49:41.596560Z

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 96777e5b-a202-4393-802c-adb2a36d9774 · inbound

From Custom-Fit to Portable: Bridging the Gap Between Synthesized and Engineered GPU Query Execution cites this paper.

From Custom-Fit to Portable: Bridging the Gap Between Synthesized and Engineered GPU Query Execution CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:45:58.679140Z

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.