Dataset · Hugging Face

RoganInglis/apps-backdoors

Name: apps-backdoors
Creator: RoganInglis
License: mit
Keywords: license:mit, size_categories:1K<n<10K, format:parquet, modality:text, library:datasets, library:dask, library:mlcroissant, library:polars, arxiv:2105.09938, arxiv:2312.06942, region:us

APPS Dataset with Backdoor Annotations This is a processed version of the APPS dataset combined with verified backdoor annotations for AI safety research, specifically for AI control experiments. Generated for use with ControlArena. Original APPS Dataset Paper: Measuring Coding Challenge Competence With APPSAuthors: Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob… See the full description on the dataset page: https://huggingface.co/datasets/RoganInglis/apps-backdoors.

View on Hugging FaceReport an issue

Author / organization	RoganInglis
License (as declared)	mit
Downloads	413 (as reported by Hugging Face)
Likes	3
Created	27 August 2025
Last updated at source	27 August 2025

Embed this entry

<iframe src="https://silytics.si/embed/item/9c3e23bc-c9f2-4ad2-9c2c-4b4ac6aab009" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from RoganInglis

RoganInglis/vllm-control-arenaDataset
RoganInglis/apps-control-arenaDataset

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.