Atlas: A Brain for Self-driving Laboratories
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Self-driving laboratories (SDLs) are next-generation research and development platforms for closed-loop, autonomous experimentation that combine ideas from artificial intelligence, robotics, and high-performance computing. A critical component of SDLs is the decision-making algorithm used to prioritize experiments to be performed. This SDL “brain” often relies on optimization strategies that are guided by machine learning models, such as Bayesian optimization. However, the diversity of hardware constraints and scientific questions being tackled by SDLs require the availability of a set of flexible algorithms that have yet to be implemented in a single software tool. Here, we report Atlas, an application-agnostic Python library for Bayesian optimization that is specifically tailored to the needs of SDLs. Atlas provides facile access to state-of-the-art, model-based optimization algorithms—including mixed-parameter, multi-objective, constrained, robust, multi-fidelity, meta-learning, and molecular optimization—as an all-in-one tool that is expected to suit the majority of specialized SDL needs. After a brief description of its core capabilities, we demonstrate Atlas’ utility by optimizing the oxidation potential of metal complexes with an autonomous electrochemical experimentation platform. We expect Atlas to expand the breadth of design and discovery problems in the natural sciences that are immediately addressable with SDLs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it