datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MagicBench
MagicBench: A Deception-Sensitive Cognitive Benchmark for LLMs
Project page | Code | Dataset
MagicBench is a deception-sensitive cognitive benchmark for language models built around magic-trick understanding. Rather than testing recall alone, it probes whether a model can reason about hidden causes, audience beliefs, violated expectations, uncertainty, and counterfactual changes in settings where the visible events are intentionally misleading.
Dataset Summary… See the full description on the dataset page: https://huggingface.co/datasets/hsiung/MagicBench.medical-cyber-train
Medical Cybersecurity Q&A Dataset
This dataset contains question-answer pairs focused on medical device cybersecurity and healthcare security.
Dataset Information
Total Q&A pairs: 523
Number of unique topics: 9
Number of unique subtopics: 48
Last updated: 2025-05-24
Topics Covered
Attack Vectors
Common Security Tools and Usage
Compliance and Legal Requirements
Exploits
Incident Response and Recovery
Internet of Medical Things (IoMT) and Medical Technologies… See the full description on the dataset page: https://huggingface.co/datasets/magichampz/medical-cyber-train.medical-cyber-test
Medical Cybersecurity Q&A Dataset
This dataset contains question-answer pairs focused on medical device cybersecurity and healthcare security.
Dataset Information
Total Q&A pairs: 113
Number of unique topics: 9
Number of unique subtopics: 46
Last updated: 2025-05-28
Topics Covered
Attack Vectors
Common Security Tools and Usage
Compliance and Legal Requirements
Exploits
Incident Response and Recovery
Internet of Medical Things (IoMT) and Medical Technologies… See the full description on the dataset page: https://huggingface.co/datasets/magichampz/medical-cyber-test.medical-cyber-val
Medical Cybersecurity Q&A Dataset
This dataset contains question-answer pairs focused on medical device cybersecurity and healthcare security.
Dataset Information
Total Q&A pairs: 112
Number of unique topics: 9
Number of unique subtopics: 48
Last updated: 2025-05-28
Topics Covered
Attack Vectors
Common Security Tools and Usage
Compliance and Legal Requirements
Exploits
Incident Response and Recovery
Internet of Medical Things (IoMT) and Medical Technologies… See the full description on the dataset page: https://huggingface.co/datasets/magichampz/medical-cyber-val.