CRANE-LLM: Runtime-Augmented LLMs for Crash Prediction and Diagnosis in ML Notebooks
cs.SE
Submitted: 2026-02-20
Updated: 2026-08-24
Code: https://github.com/PELAB-LiU/crane
Terminology
Sources
- ShapeFlow: Dynamic Shape Interpreter for TensorFlow
- An Effective Data-Driven Approach for Localizing Deep Learning Faults
- Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification
- FlowBook: Enforcing Reproducibility in Computational Notebooks
- Sparks of Artificial General Intelligence: Early experiments with GPT-4
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Qwen2.5-Coder Technical Report
- Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
- Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
- On Mitigating Code LLM Hallucinations with API Documentation
- A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair
- Automated Assertion Generation and Regression Testing for Machine Learning Notebooks
- Debug Smarter, Not Harder: AI Agents for Error Resolution in Computational Notebooks
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters