https://github.com/georgetown-cset/CSET-AIID-harm-taxonomy
Repo containing documentation and explanation for CSET's harm taxonomy of incidents from AIID.
https://github.com/georgetown-cset/CSET-AIID-harm-taxonomy
Last synced: 5 months ago
JSON representation
Repo containing documentation and explanation for CSET's harm taxonomy of incidents from AIID.
- Host: GitHub
- URL: https://github.com/georgetown-cset/CSET-AIID-harm-taxonomy
- Owner: georgetown-cset
- Created: 2023-06-27T17:23:12.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-07-25T16:43:14.000Z (over 1 year ago)
- Last Synced: 2024-05-07T18:22:52.074Z (12 months ago)
- Size: 1.11 MB
- Stars: 11
- Watchers: 7
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-machine-learning-interpretability - CSET's Harm Taxonomy for the AI Incident Database - cset/CSET-AIID-harm-taxonomy?style=social) (Community and Official Guidance Resources / Community Frameworks and Guidance)
README
# CSET's Harm Taxonomy for the AI Incident Database
This repository contains documentation and explanation for CSET's harm taxonomy of incidents from AIID.
# AI Incident Database
The [AI Incident Database](https://incidentdatabase.ai/) is a community-driven AI incident reporting site. Users are "invited to explore the incidents collected to date, view the complete listing, and submit additional incident reports. Researchers are invited to review our working definition of AI incidents."
Between June 2022 and June 2024, CSET developed and applied an AI Harm incident taxonomy to nearly 300 incidents included in the AI Incident Database. Annotation work has been discontinued, but the team is still accessible for any questions regarding the taxonomy and potential use cases.
# CSET's Harm Taxonomy
Documentation for CSET's annotation process can be found [here](https://github.com/georgetown-cset/CSET-AIID-harm-taxonomy/blob/main/CSET%20V1%20AI%20Annotation%20Guide%20(with%20Schema%20and%20Field%20Descriptions)%2025Jul2023.pdf). This schema includes the motivation for annotated fields, along with a data dictionary for the fields for assistance in data processing.