Paper Citation Record · LEDGER

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels

As of 9 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2607.24762.

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

pith.paper-citation-record.v1
2607.24762 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T12:30:32.026111Z

measured 43 of 43 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1971731f-9819-49a5-9d68-e18cae51aae1 · outbound

This paper cites Efficient processing of deep neural networks: A tutorial and survey,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Efficient processing of deep neural networks: A tutorial and survey,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:26.178857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25925247-bfd9-4f71-9fcc-0ae754836ca7 · outbound

This paper cites In-datacenter performance analysis of a tensor processing unit,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels In-datacenter performance analysis of a tensor processing unit,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:26.321349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6ff40f-c41e-42ba-b3db-daef252ba32a · outbound

This paper cites A systematic characterization of LLM inference on GPUs,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels A systematic characterization of LLM inference on GPUs,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:26.464343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f88046d-bd44-410c-b9e8-366468ef7862 · outbound

This paper cites Triton: An intermediate language and compiler for tiled neural network computations,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Triton: An intermediate language and compiler for tiled neural network computations,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:26.606355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7dec49e-6593-424e-b528-9b37879f9239 · outbound

This paper cites FlashAttention: Fast and memory-efficient exact attention with IO-awareness,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels FlashAttention: Fast and memory-efficient exact attention with IO-awareness,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:26.776342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a5c079-575a-4971-9bb1-0ae777476a47 · outbound

This paper cites Autocomp: A powerful and portable code optimizer for tensor accelerators,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Autocomp: A powerful and portable code optimizer for tensor accelerators,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:26.916959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a424d0a-ac69-4f2d-9e89-e7c6f562f746 · outbound

This paper cites Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.102520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7acecd29-b2f7-4157-84bb-80508cd4c738 · outbound

This paper cites KernelBench: Can LLMs write efficient GPU kernels?.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels KernelBench: Can LLMs write efficient GPU kernels?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.269678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf936cc-483d-4676-a6c9-198a92e5bff9 · outbound

This paper cites KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.349032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf8a3bc0-b548-4ab6-a1ce-11250e5c3b1c · outbound

This paper cites TritonBench: Benchmarking large language model capabilities for generating Triton operators,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels TritonBench: Benchmarking large language model capabilities for generating Triton operators,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.467840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee1d5d5f-ffef-448f-ba1b-f08fa11edc70 · outbound

This paper cites MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.620409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4ec3f7-dd9f-4493-8e70-bb36463823a5 · outbound

This paper cites CUDABench: Benchmarking LLMs for text-to-CUDA generation,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels CUDABench: Benchmarking LLMs for text-to-CUDA generation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.759973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69e3f430-ff49-4f17-b5fa-381b2505f563 · outbound

This paper cites BackendBench: An evaluation suite for testing how well LLMs and humans can write PyTorch backends,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels BackendBench: An evaluation suite for testing how well LLMs and humans can write PyTorch backends,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:27.914125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac666df2-100b-4f17-85ff-b6bada40bcdd · outbound

This paper cites FlashInfer- Bench: Building the virtuous cycle for AI-driven LLM systems,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels FlashInfer- Bench: Building the virtuous cycle for AI-driven LLM systems,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:28.074757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a3d9507-9764-4c7b-8de6-db46453091de · outbound

This paper cites CudaForge: An agent framework with hardware feedback for CUDA kernel optimization,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels CudaForge: An agent framework with hardware feedback for CUDA kernel optimization,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:28.230400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d0106e1-eee0-4b52-b862-7efe271f87e9 · outbound

This paper cites Astra: A multi-agent system for GPU kernel performance optimization,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Astra: A multi-agent system for GPU kernel performance optimization,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:28.429142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aac71d27-5e89-449f-8141-48457486147d · outbound

This paper cites Towards robust agentic CUDA kernel benchmarking, verification, and optimization,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Towards robust agentic CUDA kernel benchmarking, verification, and optimization,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:28.664212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe5c0d64-fea4-4f74-8e62-feac4f59f4eb · outbound

This paper cites KernelAgent: Multi-agent GPU kernel synthesis and optimization,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels KernelAgent: Multi-agent GPU kernel synthesis and optimization,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:28.844946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab9e2cb-02dd-42ab-8e22-1d56bed21f32 · outbound

This paper cites Complete anytime beam search,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Complete anytime beam search,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.054222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2048d913-47f0-4260-a38a-f78686939b10 · outbound

This paper cites Bandit based Monte-Carlo planning,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Bandit based Monte-Carlo planning,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.198605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2ad9d42-aa80-443c-96ed-3d5a88a17e51 · outbound

This paper cites Deep residual learning for image recognition,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Deep residual learning for image recognition,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.351224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 011e335f-1c45-452f-8c61-007d0a3eb00e · outbound

This paper cites Stable diffusion 3.5 medium model card,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Stable diffusion 3.5 medium model card,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.480014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4017e7e9-ff10-478a-9d07-2d1bca640a3d · outbound

This paper cites google/gemma-4-E2B-it model card,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels google/gemma-4-E2B-it model card,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.623340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d253fc1-25e5-470c-9124-7871f2c466a5 · outbound

This paper cites Qwen/Qwen3.5-35B-A3B model card,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Qwen/Qwen3.5-35B-A3B model card,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.773982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 609c88c6-3c38-4e72-9a5a-366e94dc4271 · outbound

This paper cites DGX Spark user guide: Hardware overview,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels DGX Spark user guide: Hardware overview,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:29.922278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a393e69-32a8-42b0-a8ce-719a6f99849d · outbound

This paper cites PyTorch: An imperative style, high-performance deep learning library,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels PyTorch: An imperative style, high-performance deep learning library,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:30.071296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f81cf21-94c3-4506-b1ea-468383c6dd30 · outbound

This paper cites CUDA programming guide,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels CUDA programming guide,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:30.262483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5a7e942-9b8c-4e34-b1b7-3bb10392d673 · outbound

This paper cites CUDA C++ best practices guide,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels CUDA C++ best practices guide,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:30.467461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 892d299e-27b6-4fa5-99b7-d48e9eae8511 · outbound

This paper cites Tvm: an automated end-to-end optimizing compiler for deep learning,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Tvm: an automated end-to-end optimizing compiler for deep learning,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:30.689021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ca0e47d-8324-4a05-80b1-edbf8bed4ac3 · outbound

This paper cites Learning to optimize tensor programs,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Learning to optimize tensor programs,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:30.863019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 789fd873-2679-4da6-bbdf-b6265dc57771 · outbound

This paper cites Ansor: Generating high-performance tensor programs for deep learning,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Ansor: Generating high-performance tensor programs for deep learning,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:30.945666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4beaeafd-b4d0-40dd-b4e0-4a78a707faa8 · outbound

This paper cites torchvision.models.resnet50,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels torchvision.models.resnet50,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.004673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe150bee-c4ab-46e3-ad8c-94d2388a9e38 · outbound

This paper cites Do ImageNet classifiers generalize to ImageNet?.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Do ImageNet classifiers generalize to ImageNet?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.089960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 285896f3-d2c6-45cc-8af3-49dd7d60f4de · outbound

This paper cites Diffusers: State-of-the-art diffusion models,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Diffusers: State-of-the-art diffusion models,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.198319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ebcfc4-0ac0-4268-af58-72fa2a32ac8a · outbound

This paper cites T2I-CompBench: A comprehensive benchmark for open-world compositional text-to-image generation,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels T2I-CompBench: A comprehensive benchmark for open-world compositional text-to-image generation,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.304018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a74e52e-c2df-4419-9e66-851ad5d55655 · outbound

This paper cites Judging LLM-as-a-judge with MT-Bench and chatbot arena,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Judging LLM-as-a-judge with MT-Bench and chatbot arena,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.421596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f84e7605-fc9a-495a-8aeb-063b34e1af03 · outbound

This paper cites ShareGPT Prompts Annotated,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels ShareGPT Prompts Annotated,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.503958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4060d277-5e4e-4587-ae63-2cc4018ec38f · outbound

This paper cites LongBench: A bilingual, multitask benchmark for long context understanding,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels LongBench: A bilingual, multitask benchmark for long context understanding,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.572369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf6d4265-ee8b-49e5-9bff-8447c34efbdd · outbound

This paper cites Introducing Claude Opus 4.7,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Introducing Claude Opus 4.7,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.639521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3959a1e7-6f4b-46f4-a12e-07b16174161a · outbound

This paper cites ComputeEval: Evaluating large language models on CUDA,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels ComputeEval: Evaluating large language models on CUDA,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.722780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9385890-c6d1-44c0-a485-d3b9b9803913 · outbound

This paper cites TritonGym: A benchmark for agentic LLM work- flows in Triton GPU code generation,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels TritonGym: A benchmark for agentic LLM work- flows in Triton GPU code generation,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.824296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a25549b0-c343-4c98-94ed-a52768766abf · outbound

This paper cites KernelFalcon: Deep agent architecture for autonomous GPU kernel generation,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels KernelFalcon: Deep agent architecture for autonomous GPU kernel generation,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:31.939574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87976858-c3f5-40f1-abef-9948308b0a7e · outbound

This paper cites torch.nn.functional.scaled_dot_product_attention,.

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels torch.nn.functional.scaled_dot_product_attention,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T12:30:32.026111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.