AutoRA
AutoRA: Automated Research Assistant for Closed-Loop Empirical Research - Published in JOSS (2024)
Science Score: 95.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in JOSS metadata -
○Academic publication links
-
✓Committers with academic emails
1 of 3 committers (33.3%) from academic institutions -
○Institutional organization owner
-
✓JOSS paper metadata
Published in Journal of Open Source Software
Repository
Hosts the JOSS submission for the autora framework.
Basic Info
- Host: GitHub
- Owner: AutoResearch
- License: mit
- Language: TeX
- Default Branch: main
- Size: 7.57 MB
Statistics
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 1
- Releases: 0
Metadata Files
README.md
AutoRA: Automated Research Assistant for Closed-Loop Empirical Research
This repository hosts the joint JOSS submission of the AutoRA framework.
CORE PACKAGES (required dependencies)
The AutoRA framework consists of core packages with minimal dependencies.
- autora: Main repository that hosts the documentation of autora across all vetted subpackages and serves as the main package.
- autora-core: AutoRA workflow mechanics.
- autora-synthetic: Synthetic models for benchmarking in AutoRA.
OPTIONAL PACKAGES (optional dependencies):
In addition, the AutoRA framework provides vetted optional dependencies for workflow components, including theorists (for automating model discovery), experimentalists (for automating experimental design), and experiment runners (for automating data collection).
Theorist Components: - autora[theorist-darts]: Automated model discovery with Differentiable Architecture Search. - autora[theorist-bms]: Automated model discovery with Bayesian Machine Scientist. - autora[theorist-bsr]: Automated model discovery with Bayesian Symbolic Regression.
Experimentalist Components: - autora[experimentalist-falsification]: Automated experimental design based on predicted model falsification. - autora[experimentalist-inequality]: Automated experimental design based on a pairwise distance metric. - autora[experimentalist-leverage]: Automated experimental design based on the leverage of data points on model predictions. - autora[experimentalist-mixture]: Automated experimental design based on mixture of experimentalists. - autora[experimentalist-nearest-value]: Automated experimental design based on distance to existing pool of experiment conditions. - autora[experimentalist-novelty]: Automated experimental design based on experiment novelty. - autora[experimentalist-model-disagreement]: Automated experimental design based on model disagreement. - autora[experimentalist-uncertainty]: Automated experimental design based on model uncertainty.
Experiment Runner Components: - autora[experiment-runner-firebase-prolific]: Automated data collection through serving an experiment on Firebase and recruiting participants with Prolific. - autora[experiment-runner-experimentation-manager-firebase]: Automated data collection through serving an experiment on Firebase. - autora[experiment-runner-recruitment-manager-prolific]: Automated participant recruitment with Prolific. - autora[experiment-runner-synthetic-abstract-equation]: Automated data generation based on mathematical equations.
Owner
- Name: Autonomous Empirical Research Initiative
- Login: AutoResearch
- Kind: organization
- Website: www.empiricalresearch.ai
- Repositories: 12
- Profile: https://github.com/AutoResearch
We strive to enhance and accelerate scientific discovery by automating steps in the empirical research process.
JOSS Publication
AutoRA: Automated Research Assistant for Closed-Loop Empirical Research
Authors
Brown University, USA, Osnabrück University, Germany
Brown University, USA
Brown University, USA
Brown University, USA
University of Chicago, USA
Princeton University, USA
University of Indiana, USA
Brown University, USA
Brown University, USA, Princeton University, USA
Brown University, USA
Editor
Mehmet Hakan Satman
Tags
Python automated scientific discovery symbolic regression active learning closed-loop behavioral scienceGitHub Events
Total
- Watch event: 1
- Push event: 23
- Pull request review event: 2
- Pull request event: 4
- Fork event: 1
- Create event: 1
Last Year
- Watch event: 1
- Push event: 23
- Pull request review event: 2
- Pull request event: 4
- Fork event: 1
- Create event: 1
Committers
Last synced: 7 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Sebastian Musslick | s****n@m****e | 48 |
| Younes Strittmatter | y****r@b****u | 2 |
| Mehmet Hakan Satman | m****n@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 1
- Total pull requests: 3
- Average time to close issues: N/A
- Average time to close pull requests: about 8 hours
- Total issue authors: 1
- Total pull request authors: 3
- Average comments per issue: 0.0
- Average comments per pull request: 0.33
- Merged pull requests: 3
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 2
- Average time to close issues: N/A
- Average time to close pull requests: about 1 hour
- Issue authors: 0
- Pull request authors: 2
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 2
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- musslick (1)
Pull Request Authors
- musslick (2)
- jbytecode (2)
- younesStrittmatter (1)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- actions/checkout v4 composite
- actions/upload-artifact v4 composite
- openjournals/openjournals-draft-action master composite