# GUM (General User Models)
[](https://arxiv.org/abs/2505.10831)
General User Models learn about you by observing any interaction you have with your computer. The GUM takes as input any unstructured observation of a user (e.g., device screenshots) and constructs confidence-weighted propositions that capture the user's knowledge and preferences. GUMs introduce an architecture that infers new propositions about a user from multimodal observations, retrieves related propositions for context, and continuously revises existing propositions.
## Documentation
**Please go here for documentation on setting up and using GUMs: [https://generalusermodels.github.io/gum/](https://generalusermodels.github.io/gum/)**
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## License
MIT License
## Citation and Paper
If you're interested in reading more, please check out our paper!
[Creating General User Models from Computer Use](https://arxiv.org/abs/2505.10831)
```bibtex
@misc{shaikh2025creatinggeneralusermodels,
title={Creating General User Models from Computer Use},
author={Omar Shaikh and Shardul Sapkota and Shan Rizvi and Eric Horvitz and Joon Sung Park and Diyi Yang and Michael S. Bernstein},
year={2025},
eprint={2505.10831},
archivePrefix={arXiv},
primaryClass={cs.HC},
url={https://arxiv.org/abs/2505.10831},
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/GeneralUserModels/gum",
"name": "gum-ai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": null,
"author": "Omar Shaikh",
"author_email": "Omar Shaikh <oshaikh13@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/10/4c/5f8e620432735d654a01774a2cba00300ac97710a5903c422b58aca02787/gum_ai-0.1.10.tar.gz",
"platform": null,
"description": "# GUM (General User Models)\n\n[](https://arxiv.org/abs/2505.10831)\n\nGeneral User Models learn about you by observing any interaction you have with your computer. The GUM takes as input any unstructured observation of a user (e.g., device screenshots) and constructs confidence-weighted propositions that capture the user's knowledge and preferences. GUMs introduce an architecture that infers new propositions about a user from multimodal observations, retrieves related propositions for context, and continuously revises existing propositions.\n\n## Documentation\n\n**Please go here for documentation on setting up and using GUMs: [https://generalusermodels.github.io/gum/](https://generalusermodels.github.io/gum/)**\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nMIT License\n\n## Citation and Paper\n\nIf you're interested in reading more, please check out our paper!\n\n[Creating General User Models from Computer Use](https://arxiv.org/abs/2505.10831)\n\n```bibtex\n@misc{shaikh2025creatinggeneralusermodels,\n title={Creating General User Models from Computer Use}, \n author={Omar Shaikh and Shardul Sapkota and Shan Rizvi and Eric Horvitz and Joon Sung Park and Diyi Yang and Michael S. Bernstein},\n year={2025},\n eprint={2505.10831},\n archivePrefix={arXiv},\n primaryClass={cs.HC},\n url={https://arxiv.org/abs/2505.10831}, \n}\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": null,
"version": "0.1.10",
"project_urls": {
"Homepage": "https://github.com/GeneralUserModels/gum"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2b2f28e6d8df7b9dfcd52fd5fd3d38eacce818439a79f5ae8db519c8cbd73cb4",
"md5": "bdc2bd970e036490a586adae5a489752",
"sha256": "b606b32a7eb7b19e5501ae951af958f174c03f9dfcf87852fffb0af6de669d05"
},
"downloads": -1,
"filename": "gum_ai-0.1.10-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bdc2bd970e036490a586adae5a489752",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 27823,
"upload_time": "2025-07-10T07:26:35",
"upload_time_iso_8601": "2025-07-10T07:26:35.339274Z",
"url": "https://files.pythonhosted.org/packages/2b/2f/28e6d8df7b9dfcd52fd5fd3d38eacce818439a79f5ae8db519c8cbd73cb4/gum_ai-0.1.10-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "104c5f8e620432735d654a01774a2cba00300ac97710a5903c422b58aca02787",
"md5": "79a8d1ea54d68117d834d384cce13dc7",
"sha256": "bd2caee83059b8bceca4641b5a85a96d1da12f1fd57905a11c36f7d09207748a"
},
"downloads": -1,
"filename": "gum_ai-0.1.10.tar.gz",
"has_sig": false,
"md5_digest": "79a8d1ea54d68117d834d384cce13dc7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 25983,
"upload_time": "2025-07-10T07:26:37",
"upload_time_iso_8601": "2025-07-10T07:26:37.307885Z",
"url": "https://files.pythonhosted.org/packages/10/4c/5f8e620432735d654a01774a2cba00300ac97710a5903c422b58aca02787/gum_ai-0.1.10.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-10 07:26:37",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "GeneralUserModels",
"github_project": "gum",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "gum-ai"
}
JSON
