Pith. sign in

Paper Citation Record · LEDGER

Kevin: Multi-Turn RL for Generating CUDA Kernels

As of 9 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 26 inbound Pith citation observations for arXiv:2507.11948.

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

pith.paper-citation-record.v1
2507.11948 v1

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:02:44.482544Z

measured 93 of 93 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 26 of 26 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:14:20.253791Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T22:29:00.387986Z

Reference resolution

67 of 67 outbound references displayed

  • verified exact0
  • verified fuzzy30
  • unresolved36
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0a7bd183-13a3-4e14-b694-791e652ffd31 · outbound

This paper cites Concrete problems in ai safety, 2016.

Kevin: Multi-Turn RL for Generating CUDA Kernels Concrete problems in ai safety, 2016

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:37.716853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:37.716853Z digest=sha256:9c2adc5601affe839cd435effd920f96315f91bf19c449ba241b89ca2297b67c

Observation a5e2c076-e17e-49c8-86eb-fd0b5b618a08 · outbound

This paper cites Le, Christopher Ré, and Azalia Mirhoseini.

Kevin: Multi-Turn RL for Generating CUDA Kernels Le, Christopher Ré, and Azalia Mirhoseini

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:37.770626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:37.770626Z digest=sha256:242d749225893698d72d02c264eb8ba618f0985c050fb0abc61766492ab74ce9

Observation 908ad037-323e-4663-a0c3-90e196941179 · outbound

This paper cites Gonzalez, and Ion Stoica.

Kevin: Multi-Turn RL for Generating CUDA Kernels Gonzalez, and Ion Stoica

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:37.908432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:37.908432Z digest=sha256:454e86f85e81b851f7baf16a117033f0956f5e5c945f8647ba302f933cd86f9d

Observation 264218f1-5fe7-4531-8718-759822c4f075 · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:38.046691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.046691Z digest=sha256:5f80a38a77837e0f6863060927a651e636c2430f806db75ef19b07c7b014a59a

Observation 486c0110-96a0-423a-97e7-5752f0e22b55 · outbound

This paper cites Automating gpu kernel generation with deepseek- r1 and inference-time scaling.

Kevin: Multi-Turn RL for Generating CUDA Kernels Automating gpu kernel generation with deepseek- r1 and inference-time scaling

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:50.570501Z

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.

source=pdf_text observed=2026-08-06T17:02:38.147054Z digest=sha256:e5f89f725abd921459fee1546fff8e4de5c107689cbd10fba44b90d04c4c98f5

Observation 7c94f462-af32-41d0-87f2-7a6e94890428 · outbound

This paper cites Warpdrive: An agentic workflow for ninja gpu transformations.

Kevin: Multi-Turn RL for Generating CUDA Kernels Warpdrive: An agentic workflow for ninja gpu transformations

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:50.231647Z

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.

source=pdf_text observed=2026-08-06T17:02:38.300229Z digest=sha256:f420b51d3c04891098d04d0b3b55f09309a0f69b556e0059566e5ed58c1520b7

Observation 370f31e3-e3a4-4378-b821-34877dea68ac · outbound

This paper cites Flashattention-2: Faster attention with better parallelism and work partitioning, 2023.

Kevin: Multi-Turn RL for Generating CUDA Kernels Flashattention-2: Faster attention with better parallelism and work partitioning, 2023

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:38.412758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.412758Z digest=sha256:1e700fd6f56200e7be2589ea95047c84111391d99f5093f32f506dddce29ff41

Observation 8401544f-6539-406d-adea-773b174f9047 · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Kevin: Multi-Turn RL for Generating CUDA Kernels Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:38.515282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.515282Z digest=sha256:f257d272c5ee2dc35c69f1042ec78e80472bff4886f52fc5bb307d58b840a727

Observation 78d9d8b4-9497-48f0-8e98-d64f1ed5b6d4 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:38.628308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.628308Z digest=sha256:bf2aa15a82ff7be5f43a8a8ce399d2824b7346a06a857d8ff4fd0a3a35099c74

Observation 5b4641b1-e88f-4149-96af-a34f9200e92b · outbound

This paper cites Gemini 2.5: Our most intelligent models are getting even bet- ter.

Kevin: Multi-Turn RL for Generating CUDA Kernels Gemini 2.5: Our most intelligent models are getting even bet- ter

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:50.044013Z

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.

source=pdf_text observed=2026-08-06T17:02:38.711064Z digest=sha256:e9961af9b4e82ea23bf3795b239eb6b6e3f220fb9819e4f1b112ca2e04c2d914

Observation 6cf5fccd-df10-476c-89eb-917149a0dab0 · outbound

This paper cites Bartlett, Ilya Sutskever, and Pieter Abbeel.

Kevin: Multi-Turn RL for Generating CUDA Kernels Bartlett, Ilya Sutskever, and Pieter Abbeel

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:38.800696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.800696Z digest=sha256:475b08bacbe505ea757dbe862ac474558084b1f30c3453218d4774cc8e7d8df1

Observation 5c0292a5-2658-44dd-abb4-83e6b2b5e678 · outbound

This paper cites Codemonkeys: Scaling test-time compute for software engineering, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Codemonkeys: Scaling test-time compute for software engineering, 2025

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:38.917350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.917350Z digest=sha256:c64842e4d84d96c0d35979891e52fbfd00b8e39d314622bb0ad27eb49ea16faa

Observation dbfa5d30-c513-4a6d-850d-a4290c812794 · outbound

This paper cites Rlef: Grounding code llms in execution feedback with reinforcement learning, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Rlef: Grounding code llms in execution feedback with reinforcement learning, 2025

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:39.032733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:39.032733Z digest=sha256:780d02cfedd8708c46c960bf033210d3e074c8d5ef3859ef2d90e317a6f25ead

Observation ab71fa39-8595-4a41-8c0e-3d490ebba9cc · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-06T17:02:49.851401Z

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.

source=pdf_text observed=2026-08-06T17:02:39.123994Z digest=sha256:d430e66c5d6c9497101b6c66bcf0b6cda15773d66953e4a0e6bc89f85e559ea5

Observation b2f20324-459e-41a5-a330-a0267c0dfe81 · outbound

This paper cites Alphaevolve: A gemini-powered coding agent for designing advanced algorithms, May 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Alphaevolve: A gemini-powered coding agent for designing advanced algorithms, May 2025

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:49.722393Z

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.

source=pdf_text observed=2026-08-06T17:02:39.223028Z digest=sha256:d5e88986bd34daea876e020657eb973217a65bcc10edbfbd33953acfb95a10ca

Observation adda0869-c854-408e-ac5a-d58827759369 · outbound

This paper cites Openrlhf: An easy-to-use, scalable and high-performance rlhf framework, 2024.

Kevin: Multi-Turn RL for Generating CUDA Kernels Openrlhf: An easy-to-use, scalable and high-performance rlhf framework, 2024

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:49.573632Z

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.

source=pdf_text observed=2026-08-06T17:02:39.280864Z digest=sha256:836de4ddf723e41007b4e7ed31dc3270e8bdca0ee285e3667165b7ce654be6a5

Observation 9c017636-41aa-43bb-bf7f-b490aa865b74 · outbound

This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan.

Kevin: Multi-Turn RL for Generating CUDA Kernels Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:39.365559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:39.365559Z digest=sha256:f6647aa4674c6af7eaef7220d646b5408e99b008e02e0ca908d707a22720de9c

Observation 3f538d22-e0cd-467f-ad65-b57332470382 · outbound

This paper cites The stack: 3 tb of permissively licensed source code, 2022.

Kevin: Multi-Turn RL for Generating CUDA Kernels The stack: 3 tb of permissively licensed source code, 2022

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:39.454227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:39.454227Z digest=sha256:21ecef008de1722d28c22cbef813b2fce8d328f5cd7dd29aa68e43a66dcf38f4

Observation 994d721d-8ef2-4570-881c-fe7542d6400a · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Kevin: Multi-Turn RL for Generating CUDA Kernels Gonzalez, Hao Zhang, and Ion Stoica

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:49.420206Z

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.

source=pdf_text observed=2026-08-06T17:02:39.579448Z digest=sha256:0c7bb6ea4ce781a4c2756f542ab0d936a18404a7b893a348844c5dce34606312

Observation 985963c8-f033-409a-920e-90e66ba15741 · outbound

This paper cites Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D.

Kevin: Multi-Turn RL for Generating CUDA Kernels Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:39.670738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:39.670738Z digest=sha256:ecf67e34ab989ac84e3e82d2e7cbf3f360119cb6ee91abaca18385be58eadea4

Observation ea6ec814-cef0-4f46-b399-a188e62a4ca1 · outbound

This paper cites The ai cuda engineer: Agentic cuda kernel discovery, optimization and composition, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels The ai cuda engineer: Agentic cuda kernel discovery, optimization and composition, 2025

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:49.252860Z

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.

source=pdf_text observed=2026-08-06T17:02:39.810647Z digest=sha256:af231404728083553bbda7a4c3f9b083001dbd5efd05ab1a8e919cf929419ba8

Observation fbbd5c5c-1d72-40ee-8b94-5cbd3a3a7355 · outbound

This paper cites Tritonbench: Benchmarking large language model capabilities for generating triton operators, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Tritonbench: Benchmarking large language model capabilities for generating triton operators, 2025

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:39.889019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:39.889019Z digest=sha256:e35c17cc59c43b8c542177ed10f9c12aca518414af6a43f383785b4f1da25e14

Observation 9f951b42-dbe5-4b0d-9d1d-f0f4e15e132c · outbound

This paper cites Starcoder: may the source be with you!, 2023.

Kevin: Multi-Turn RL for Generating CUDA Kernels Starcoder: may the source be with you!, 2023

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:49.082607Z

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.

source=pdf_text observed=2026-08-06T17:02:40.058883Z digest=sha256:ad2dedf78a9b786eb6689a6a82f4d0611274bb025eb3ab958a889bc722fdf2fc

Observation a8f83dc6-396b-4c8b-ae39-af5869b70f18 · outbound

This paper cites Rltf: Reinforcement learning from unit test feedback, 2023.

Kevin: Multi-Turn RL for Generating CUDA Kernels Rltf: Reinforcement learning from unit test feedback, 2023

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:48.934917Z

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.

source=pdf_text observed=2026-08-06T17:02:40.131633Z digest=sha256:4031481fac165eeb9034f4e96139442fc69e2d19ccc4612f56868873a66d23a9

Observation 6e3c9e77-8c31-4a7d-a15c-b33dd2abef31 · outbound

This paper cites Understanding r1-zero-like training: A critical perspective, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Understanding r1-zero-like training: A critical perspective, 2025

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:40.230633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:40.230633Z digest=sha256:aaac999ff60d89baf3fbe3a588b97b35e3b71d54f1288f83080e0ab63155d9e4

Observation 8a78a428-35c7-487f-93e8-6dac163f1c63 · outbound

This paper cites Deepcoder: A fully open-source 14b coder at o3-mini level.

Kevin: Multi-Turn RL for Generating CUDA Kernels Deepcoder: A fully open-source 14b coder at o3-mini level

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:48.735720Z

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.

source=pdf_text observed=2026-08-06T17:02:40.319204Z digest=sha256:5c5ddd3cfc651ff4d308355dbd88f81d6ba6aeabccf695e8803c4534be2988b1

Observation 3820b2c3-5891-45c4-a740-bead6bf69795 · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Sto- ica.

Kevin: Multi-Turn RL for Generating CUDA Kernels Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Sto- ica

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:48.526909Z

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.

source=pdf_text observed=2026-08-06T17:02:40.392131Z digest=sha256:9316028ceb217d3e392879a65b7377b3f35385df57bc9c14101cd6f9ae57e051

Observation 5142138f-e7d3-483c-83a3-2f56393ed435 · outbound

This paper cites Measuring automated kernel engineering, February 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Measuring automated kernel engineering, February 2025

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:48.385886Z

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.

source=pdf_text observed=2026-08-06T17:02:40.479226Z digest=sha256:ff07f58b967c4dcaaa92130236a1b57bd95f7c4b4b938fab13be5b58b333d15e

Observation 19c8e387-3eb3-4479-b82a-d23999ecca0f · outbound

This paper cites Scalable parallel programming with cuda.

Kevin: Multi-Turn RL for Generating CUDA Kernels Scalable parallel programming with cuda

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:48.230006Z

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.

source=pdf_text observed=2026-08-06T17:02:40.634379Z digest=sha256:4b7023dd786dded3d650af20ddd4201c484f6d627b7b6c17d6a6c4cb1586c92e

Observation 599a9aa2-242e-49ba-a9ca-591ec0f3ee9b · outbound

This paper cites Lee, Ed H.

Kevin: Multi-Turn RL for Generating CUDA Kernels Lee, Ed H

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:48.128205Z

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.

source=pdf_text observed=2026-08-06T17:02:40.744190Z digest=sha256:a5d58378bf1f9560bff9695d8e7078f4cbcc99a4a4c9e588f31c1ccece3f2d00

Observation 7fcfb524-b4f7-456c-8370-c5e3bb0b5b5b · outbound

This paper cites Gpu mode at nvidia gtc 2025, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Gpu mode at nvidia gtc 2025, 2025

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:47.998420Z

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.

source=pdf_text observed=2026-08-06T17:02:40.821890Z digest=sha256:939e6c0d613d2c74a096310ebefe3de852f04c745f66457f5edd248095fea9be

Observation b43bf19a-f50d-4911-a7f0-2b96b7b57986 · outbound

This paper cites Cutlass: Cuda templates for linear algebra subroutines, May 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Cutlass: Cuda templates for linear algebra subroutines, May 2025

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:47.862699Z

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.

source=pdf_text observed=2026-08-06T17:02:40.922902Z digest=sha256:fcad015d8c4dda811848217ad3bd28bb85c2e6a7fafc8f6d4e2e07b89f4f144b

Observation 1828f03e-cde0-45e5-b15f-075b54006f98 · outbound

This paper cites Zhang, William Hu, Christopher Ré, and Azalia Mirhoseini.

Kevin: Multi-Turn RL for Generating CUDA Kernels Zhang, William Hu, Christopher Ré, and Azalia Mirhoseini

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:41.007723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:41.007723Z digest=sha256:682ceccca222d41cbaff31eb135b37350484b8cc8d516da235556be89123884e

Observation ec612b63-b133-419e-a852-7e0a9d80dd9c · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-06T17:02:47.740822Z

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.

source=pdf_text observed=2026-08-06T17:02:41.166521Z digest=sha256:e743ec90bfd1bc43ae2d8b986a27c0bc7c5d7ef33315717c9b5cebe0f6d6d7ec

Observation b6e797ff-9c65-41be-95bb-9919601a1ceb · outbound

This paper cites Putting the value back in rl: Better test-time scaling by unifying llm reasoners with verifiers, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Putting the value back in rl: Better test-time scaling by unifying llm reasoners with verifiers, 2025

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:47.585512Z

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.

source=pdf_text observed=2026-08-06T17:02:41.287739Z digest=sha256:221d3fd8266071827ac26baf6c6fb7ce1e65d80c33702b1ccc8c0d8ec4c1e125

Observation 4fe2a9fa-629e-45e7-82f7-4229c247c509 · outbound

This paper cites Llms are greedy agents: Effects of rl fine-tuning on decision-making abilities, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Llms are greedy agents: Effects of rl fine-tuning on decision-making abilities, 2025

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:41.365977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:41.365977Z digest=sha256:6adc409fe22cc61873165b2cffcbfd2b4b1664253148ea2a5c0e228ba0de2bfc

Observation c836b34c-cedd-4407-a84a-3929f95b46ea · outbound

This paper cites Proximal policy optimization algorithms, 2017.

Kevin: Multi-Turn RL for Generating CUDA Kernels Proximal policy optimization algorithms, 2017

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:41.426044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:41.426044Z digest=sha256:f1d9e73969206f9f164407d28d102404d55765c22d147e222404038d0171ce5a

Observation b6d68860-f949-4439-87f7-0b5e5991ae9d · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-06T17:02:47.412569Z

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.

source=pdf_text observed=2026-08-06T17:02:41.522138Z digest=sha256:629931ba39d25a657ea2f2f9bc6d1095632b4ad6fa9c964db9f7365636afe891

Observation e8f066b2-7645-4f43-8b42-b21236371ce2 · outbound

This paper cites Learning performance-improving code edits, 2024.

Kevin: Multi-Turn RL for Generating CUDA Kernels Learning performance-improving code edits, 2024

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:41.621229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:41.621229Z digest=sha256:dea277c11fc558512dcfb42c95df76fde661e9a88d8f741ab65ce559f665dfcb

Observation c6f27d15-1239-441f-ba9f-2b284b44abf1 · outbound

This paper cites Mastering chess and shogi by self-play with a general reinforcement learning algorithm, 2017.

Kevin: Multi-Turn RL for Generating CUDA Kernels Mastering chess and shogi by self-play with a general reinforcement learning algorithm, 2017

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:41.736142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:41.736142Z digest=sha256:f446a3969f7beb714784aadbbd9b895c7134378067ecb5c62ad9762e227a3bae

Observation 45a75b80-3026-4195-8576-16949a5ca949 · outbound

This paper cites Scaling llm test-time compute optimally can be more effective than scaling model parameters, 2024.

Kevin: Multi-Turn RL for Generating CUDA Kernels Scaling llm test-time compute optimally can be more effective than scaling model parameters, 2024

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:41.844789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:41.844789Z digest=sha256:1a602884e04136ac8e2c89c52e7d665dea4294c025f2ca346f3c45d8ff2ece1e

Observation ae984368-78e2-494f-99aa-c2b3f3ea0a5c · outbound

This paper cites Spector, Simran Arora, Aaryan Singhal, Daniel Y.

Kevin: Multi-Turn RL for Generating CUDA Kernels Spector, Simran Arora, Aaryan Singhal, Daniel Y

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:47.274098Z

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.

source=pdf_text observed=2026-08-06T17:02:41.933987Z digest=sha256:22f80bf5d7fc94ff8d99fa68f5375e66ca7edb8160dcfe29c1f217e99dc3c0f7

Observation 83cd90d4-c30d-42ab-b147-ef16c01e9f67 · outbound

This paper cites Training a generally curious agent, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Training a generally curious agent, 2025

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:47.174414Z

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.

source=pdf_text observed=2026-08-06T17:02:42.033903Z digest=sha256:d0b45c5d16ba530952de57baf51eafeb61474687493f47d032fc037b126b9127

Observation af9ae08a-7ba4-467b-b614-cac24938be24 · outbound

This paper cites Kimi k1.5: Scaling reinforcement learning with llms, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Kimi k1.5: Scaling reinforcement learning with llms, 2025

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:42.120434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:42.120434Z digest=sha256:ac728b9ca0917f0cf35381ad4beba996499b9a3445a6ee1f1b5c97210441c696

Observation 42140f02-9784-4ffb-bb11-b7c00a515fcc · outbound

This paper cites Sky-t1: Train your own o1 preview model within $450.

Kevin: Multi-Turn RL for Generating CUDA Kernels Sky-t1: Train your own o1 preview model within $450

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:42.215393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:42.215393Z digest=sha256:8785dd84af70d179d100931f79aa518cf2ec4bf416e2986d706449fa12e448ea

Observation 1ee8bf8e-6f57-4746-b41d-ee73f2e5e71a · outbound

This paper cites Intellect-2: A reasoning model trained through globally decentralized reinforcement learning, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Intellect-2: A reasoning model trained through globally decentralized reinforcement learning, 2025

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:46.993805Z

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.

source=pdf_text observed=2026-08-06T17:02:42.329149Z digest=sha256:ddb93eb4f485946ee7e010ddb30f20a498ce43e5b43ef0e3de31577b8597ed5a

Observation ca789807-ab56-4df6-be1c-6b82bc6c5408 · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:42.457168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:42.457168Z digest=sha256:ef20592b88c0900e22a5469f673507259443f5fe0b807365828e27b5b5a0de68

Observation 4bdd59a0-a8a3-4cb3-8f8c-3d9386aa5ea1 · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:42.564921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:42.564921Z digest=sha256:ffd5d3fc36d391d5bfa3ace25db8b1dd9e8da06198342d96a644dd025796a074

Observation 6e583a8a-9b63-47b9-8029-da0fd197eec4 · outbound

This paper cites Ecco: Can we improve model-generated code efficiency without sacrificing functional correctness?, 2024.

Kevin: Multi-Turn RL for Generating CUDA Kernels Ecco: Can we improve model-generated code efficiency without sacrificing functional correctness?, 2024

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:46.851958Z

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.

source=pdf_text observed=2026-08-06T17:02:42.665133Z digest=sha256:c824ae65b7ff9f8f4fcc1018e0760a30971815e6d358ac9a65b8e38881e2ac69

Observation 34c42493-cd15-4ec1-b0e9-491bb6ba8972 · outbound

This paper cites Zero++: Extremely efficient collective commu- nication for giant model training, 2023.

Kevin: Multi-Turn RL for Generating CUDA Kernels Zero++: Extremely efficient collective commu- nication for giant model training, 2023

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:46.680216Z

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.

source=pdf_text observed=2026-08-06T17:02:42.761210Z digest=sha256:f1494fc6b207024f6ce7504ad37975be805b6852f9bee9800c244577ad7822cd

Observation 162d1052-4331-4ebf-953e-d861458fc221 · outbound

This paper cites Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H.

Kevin: Multi-Turn RL for Generating CUDA Kernels Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:42.882939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:42.882939Z digest=sha256:05995776b958dd1fb8163a57007be8968e67a6f8db107c9a7b2593859c121455

Observation a2a60b80-3d23-4caf-8cba-0e6c4d649727 · outbound

This paper cites Reinforcement learning for reasoning in large language models with one training example, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Reinforcement learning for reasoning in large language models with one training example, 2025

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:46.531676Z

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.

source=pdf_text observed=2026-08-06T17:02:43.027151Z digest=sha256:abaca0c8b4ebf6df24e28062da88bd0cad707a302f18308a0272779f89f03227

Observation a0624456-b9ae-4fac-a8f9-a2be7bc54a56 · outbound

This paper cites Ragen: Understanding self-evolution in llm agents via multi-turn reinforcement learning, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Ragen: Understanding self-evolution in llm agents via multi-turn reinforcement learning, 2025

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:46.400868Z

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.

source=pdf_text observed=2026-08-06T17:02:43.209627Z digest=sha256:a3b03e1a5485212b09a54594cab67d49c45979056edbe1a985b0f2d7043ce664

Observation a07e7628-9de1-4bd5-8bb2-8e0e52a459ec · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 54

Resolution
unresolved
raw_fallback, observed 2026-08-06T17:02:46.243865Z

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.

source=pdf_text observed=2026-08-06T17:02:43.323381Z digest=sha256:e493152e31a38f9323fe6ffa2d1879dca8e8607280f7cf1fac707f4eaa1199d1

Observation 88cdb48e-9a3f-436e-8e8f-82d24cdb4792 · outbound

This paper cites Towards system 2 reasoning in llms: Learning how to think with meta chain-of-thought, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Towards system 2 reasoning in llms: Learning how to think with meta chain-of-thought, 2025

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:46.083782Z

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.

source=pdf_text observed=2026-08-06T17:02:43.416387Z digest=sha256:661d35e6232944c70cbda0b84ccb618460b93a9217379878dd9cc654b0ebbf8b

Observation 89100833-2cca-4c22-811e-b7f46327ee73 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

Kevin: Multi-Turn RL for Generating CUDA Kernels FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:43.507686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:43.507686Z digest=sha256:64792e5d45847f7f9255c1492ac598458cdeccca3216d11a65cba8b819b0b59f

Observation edd9555f-c826-4668-aadc-242e257794aa · outbound

This paper cites Dapo: An open-source llm reinforcement learning system at scale, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Dapo: An open-source llm reinforcement learning system at scale, 2025

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:43.639280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:43.639280Z digest=sha256:ccda99f2c77b9eb482b38391dcabe646c1681a0bcb930f6e5f4dc105f8b15b24

Observation c4f35d49-41f7-40be-af7c-a17f4a6accca · outbound

This paper cites Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model?, 2025.

Kevin: Multi-Turn RL for Generating CUDA Kernels Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model?, 2025

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:43.732164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:43.732164Z digest=sha256:3a4632668e3157ea9f5d8ca8e6b537c594b025534d43ee902b46274cef04e871

Observation 2405bc32-944f-4c1c-9e44-e8e1880a011f · outbound

This paper cites Deepgemm: clean and efficient fp8 gemm kernels with fine-grained scaling.

Kevin: Multi-Turn RL for Generating CUDA Kernels Deepgemm: clean and efficient fp8 gemm kernels with fine-grained scaling

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:45.925455Z

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.

source=pdf_text observed=2026-08-06T17:02:43.849821Z digest=sha256:d3f778ce37850fa8cd873a35116f88ad2add0a240aaf717b61323faf242af295

Observation 3f4041b6-18c6-4acc-b75a-4324cafd5f7e · outbound

This paper cites Minif2f: a cross-system benchmark for formal olympiad-level mathematics, 2022.

Kevin: Multi-Turn RL for Generating CUDA Kernels Minif2f: a cross-system benchmark for formal olympiad-level mathematics, 2022

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-06T17:02:43.932409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:43.932409Z digest=sha256:cebc6e390c3bc37bfda78c0243063fdc4d76d488e2fc473eb7550eae10123cfa

Observation b1af03eb-87e9-41f6-a408-478fb64d873c · outbound

This paper cites Archer: Training language model agents via hierarchical multi-turn rl, 2024.

Kevin: Multi-Turn RL for Generating CUDA Kernels Archer: Training language model agents via hierarchical multi-turn rl, 2024

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:45.685674Z

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.

source=pdf_text observed=2026-08-06T17:02:44.021267Z digest=sha256:9f27b6e604a2e4b76d572b8ea45abe62be492bb817f1b0c9e37c903c7c9487a4

Observation d039b341-9518-4f29-852b-e212aa614854 · outbound

This paper cites Improving multi-turn tool use with reinforcement learning.

Kevin: Multi-Turn RL for Generating CUDA Kernels Improving multi-turn tool use with reinforcement learning

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:45.487366Z

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.

source=pdf_text observed=2026-08-06T17:02:44.107767Z digest=sha256:677b2e9f007af17de6f4d590ab437d9210fd48035e74039aa55d3e4e39577b31

Observation dbc77750-81a4-430c-88d1-3a78e80d79ed · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 64

Resolution
unresolved
raw_fallback, observed 2026-08-06T17:02:45.320141Z

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.

source=pdf_text observed=2026-08-06T17:02:44.231115Z digest=sha256:3f1f9e59a8a8dd10dd75a8ab9cd6facd0542ba13e90130095f1c7cb0f65149dd

Observation 291afe17-dd9b-485d-886f-3edd0c74f5d8 · outbound

This paper cites We also ask it to generate sample tensor sizes for the task.

Kevin: Multi-Turn RL for Generating CUDA Kernels We also ask it to generate sample tensor sizes for the task

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:45.072245Z

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.

source=pdf_text observed=2026-08-06T17:02:44.338778Z digest=sha256:721aa1f087429e1b3b4a51cc87c87d57840a34bb9933a172b01268c426831b18

Observation 6da7b0f1-4772-4d92-9e7c-df10dc8e5c98 · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 66

Resolution
unresolved
raw_fallback, observed 2026-08-06T17:02:44.927750Z

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.

source=pdf_text observed=2026-08-06T17:02:44.408209Z digest=sha256:a010d010163c27f3255505f6cbfae48c71fcb2506925541f58832755d3462efd

Observation 06f89d91-28ad-416e-a5b0-bb39d977de76 · outbound

This paper cites "" 7 Simple model that performs Layer Normalization. 8.

Kevin: Multi-Turn RL for Generating CUDA Kernels "" 7 Simple model that performs Layer Normalization. 8

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T17:02:44.729040Z

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.

source=pdf_text observed=2026-08-06T17:02:44.482544Z digest=sha256:017b0e9afaf32a4629d96ff16197a8623e4ac889c67b7a9b842552d315877176

Observation 6fea800c-415e-45cc-9ebe-8f3dec6e0287 · outbound

This paper cites an unresolved cited work.

Kevin: Multi-Turn RL for Generating CUDA Kernels Unresolved cited work

Reference 2025

Resolution
parse uncertain
no resolver link, observed 2026-08-06T17:02:38.223669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:02:38.223669Z digest=sha256:6671f981a347aa4c12f7c65cf320cef5d58b3c8ce7451b2a7c5a00c195ab0d8c

Pith citing papers

Observation 535ee78e-d49f-4a8e-94c9-c5b3e57f91fa · inbound

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning cites this paper.

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-03T19:04:27.222436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T19:04:27.222436Z digest=sha256:6e38c647faaff22ed1f784c6ebdeb8ed7466fd894cf1d06ce6ec83b7deac9ced

Observation e063c74a-bf05-49cb-808f-89a132b5fac5 · inbound

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta cites this paper.

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-03T13:45:23.116995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T13:45:23.116995Z digest=sha256:e2d5b29204eb8cb864662cb81fead8447d338d7bf855fa4b4db9a6589cb4d46a

Observation 9fba3d5f-733d-4ee9-99d1-7f48f8b58973 · inbound

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization cites this paper.

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-21T10:20:00.045508Z

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.

source=pdf_text observed=2026-05-21T10:16:15.305706Z digest=sha256:0d2f6a44842950058bb3dbd72e2004fe3e9cb01ce184c12116c588fa198cb499

Observation 3f03d00a-cb56-4945-9ba7-03aa5b4764fd · inbound

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization cites this paper.

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-14T22:18:04.181510Z

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.

source=pdf_text observed=2026-05-14T22:17:13.431164Z digest=sha256:a32c0a56b94832e778e10a7b1497eca028679761698f103f3c8a5b62267fb9aa

Observation 3faded56-c20c-4182-b3db-3ba1b81f46cd · inbound

InCoder-32B-Thinking: Industrial Code World Model for Thinking cites this paper.

InCoder-32B-Thinking: Industrial Code World Model for Thinking Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-13T18:58:08.660491Z

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.

source=pdf_text observed=2026-05-13T18:56:31.975626Z digest=sha256:345f26dee394cff3ad9f31383415ad533327e24508cb6fdfa4131cb3aa3a3f07

Observation 2d0e2179-5344-4719-be68-2fc528e8caac · inbound

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation cites this paper.

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 3

Resolution
metadata mismatch
arxiv_id, observed 2026-05-10T09:08:25.936470Z

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.

source=pdf_text observed=2026-05-10T08:27:56.130579Z digest=sha256:45d2db4a8f1c4fe373dca50d0b41573e1391c5864bd55c2b59363737ac06fb18

Observation ca411864-36f3-4ac9-b7e4-f52c4b3bbef7 · inbound

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging cites this paper.

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-12T01:46:14.213083Z

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.

source=pdf_text observed=2026-05-12T01:43:06.644640Z digest=sha256:3211b2671a8bd0f789e11e3a17a07370cce6d0eac757b978a7547b85d0f0c5c6

Observation 6eeff244-acd2-4e8c-beec-43828bc6bb5d · inbound

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging cites this paper.

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-07-01T13:35:46.950818Z

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.

source=pdf_text observed=2026-06-30T22:54:20.299335Z digest=sha256:7abe8c1b69f973b0552c47601c13d8faf0de179756b9cf095ad0ba6df486b0d6

Observation c72586f9-17b9-4895-aa2b-08df83060519 · inbound

CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs cites this paper.

CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-12T03:26:19.470835Z

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.

source=pdf_text observed=2026-05-12T03:24:06.877354Z digest=sha256:15e94ea5b903c2e4e041a5378955b70ee15f94a08eae1b2bbccad4ced80e2e9c

Observation 0a80694b-cb1f-422f-8b56-397975b7356f · inbound

FastKernels: Benchmarking GPU Kernel Generation in Production cites this paper.

FastKernels: Benchmarking GPU Kernel Generation in Production Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-25T05:20:24.404916Z

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.

source=pdf_text observed=2026-05-25T05:20:08.724490Z digest=sha256:3dbee54cd02bc41f2c3e66b3d8942c445995c0f34b4aa2c9e42c396e78879d9c

Observation 79b45b7d-ce51-42be-9fc4-c64ebd7345fa · inbound

Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization cites this paper.

Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 6

Resolution
verified exact
arxiv_id, observed 2026-06-29T23:24:01.864782Z

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.

source=pdf_text observed=2026-06-29T23:16:05.110912Z digest=sha256:e77f06adced60e00d2b82a5e9fab6399c449081f4140965970abdb227e73729c

Observation 7fa4db39-d853-4e15-9333-61b9aaad65f7 · inbound

Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages cites this paper.

Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-06-29T12:33:24.684781Z

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.

source=arxiv_source observed=2026-06-29T12:26:23.359699Z digest=sha256:fdb7e6e283e7f21c485b6f0e0bbb799938ece272ca6811ae61c08dd9cbb7a4b6

Observation f0273d78-45dd-4ddd-a287-1356ef9dc343 · inbound

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation cites this paper.

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-06-29T07:53:13.251882Z

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.

source=pdf_text observed=2026-06-29T07:53:06.859337Z digest=sha256:c41016be52ff38b3816c1ee0908433afbcfe7a94a9ff761babd406eaf17ae17f

Observation 425de9c4-8294-40a6-836d-03a2e901d2a1 · inbound

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts cites this paper.

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-06-30T23:35:07.157854Z

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.

source=pdf_text observed=2026-06-30T23:33:47.477482Z digest=sha256:eb8e77522cb82d00ee4d4e54efa8a7aafa002df2d9a2fdd1d40891e41dc69459

Observation 8d22d16c-a45a-4d68-b026-0fe2912237ef · inbound

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts cites this paper.

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T05:17:04.965673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T05:17:04.965673Z digest=sha256:cfbb72422553a6c2e890734044363cab20445b1a13ab393ddf84a9e118656761

Observation 0043db8c-d393-48c1-9038-9a0667192661 · inbound

SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation cites this paper.

SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-07-03T22:29:00.389666Z

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.

source=pdf_text observed=2026-06-26T23:35:32.175768Z digest=sha256:b1c85adb9d64f4cfdd0f287afe4880a10bff24047e4aed2cfa35dc53174ee916

Observation f0db2be6-dc3d-4c4e-9131-33c35e2aaf72 · inbound

The FIL Hypothesis: Inductive Biases Help with Kernel Engineering cites this paper.

The FIL Hypothesis: Inductive Biases Help with Kernel Engineering Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-06-30T08:24:26.952647Z

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.

source=pdf_text observed=2026-06-30T06:06:37.832064Z digest=sha256:c75be5a58b1b9cb1ff1159d567f8f4bb35f70b6b3d7f32959043472cf169130f

Observation 84b02818-876b-42a6-8020-54e257458065 · inbound

Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation cites this paper.

Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-07-03T15:08:32.483938Z

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.

source=pdf_text observed=2026-07-03T15:01:18.911340Z digest=sha256:659d4becc396c20ad0615084278ccc5162d89cdd861d1887140525142e7ce387

Observation 5cacdf76-dff1-4988-88f2-57f624e95e67 · inbound

Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation cites this paper.

Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-12T08:42:42.063339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-12T08:42:42.063339Z digest=sha256:fbd2b2e5280091c3e1bc3815cc1fbd4ec2292aa598725c0a47d3eb10832e90ac

Observation c8e838f2-032c-4fd8-b861-5e53725559d9 · inbound

FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications cites this paper.

FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-01T15:52:50.146953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T15:52:50.146953Z digest=sha256:34ae745a7f6b3bd5b9a5d4ce402b49107b1969430eb0bf17c4b328cd8d43ac30

Observation c7930720-6f3c-4bcc-bd0a-d0a1e1c2176e · inbound

CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits cites this paper.

CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:50.753543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:50.753543Z digest=sha256:4adce36456e4750fb2f1567cea98ebb42ce75eef3773b57c6406d620d4ef75a4

Observation d769efeb-4aa7-474b-a42f-033ec73217b6 · inbound

Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization cites this paper.

Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T03:42:32.030503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T03:42:32.030503Z digest=sha256:79a61dee15cfbd386067009ec56e80ac1214956ea10e688348f1dfc29210595b

Observation 4d30955d-56b6-4ef1-aefe-c3be1ffca171 · inbound

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation cites this paper.

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T10:53:44.502494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:53:44.502494Z digest=sha256:8960cf56a56b96aec278c36804b3f52fd1dfad9d32f697a208062e70a525f44a

Observation 147af661-1cf0-4198-bd16-8bee0bd98adf · inbound

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation cites this paper.

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T10:53:44.585663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:53:44.585663Z digest=sha256:b62989fedb067c4499f183a7a884c820ed6542b55d26fbab5ac714b535f969d7

Observation eaf5dee3-c334-4d6b-ae4b-a95509097072 · inbound

AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies cites this paper.

AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T04:39:20.468386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:39:20.468386Z digest=sha256:3b0f744088274b1c0734f4c910cf68313d3a12b3a3bda4cc2dcdb5152c01c35d

Observation 15b11f46-69ff-44f9-ad14-dc34a5344dc9 · inbound

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators cites this paper.

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators Kevin: Multi-Turn RL for Generating CUDA Kernels

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-07T00:14:20.253791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:14:20.253791Z digest=sha256:5461ebc290c1c6dd4e08d22f943d07afdb9a51cc21a002e043d5af78ca6c17c8