Democratizing self-driving labs through user-developed automation infrastructure
Bibliographic record
Abstract
As self-driving labs become widely deployed in chemicals and materials research, interest in democratizing access to these platforms is growing. SDLs can be democratized by lowering their costs to increase accessibility and by creating systems that allow researchers to modify, extend, and share SDL tools to meet the needs of their science and contribute to the advancement of the SDL community. In particular, user-developed automation infrastructure is an important component of democratized SDL ecosystems. To advance community adoption of democratized SDL practices, we organized the “Democratizing Self-Driving Labs” workshop held at the 2024 Accelerate conference. As part of this workshop, the authors contributed to a demonstration of their user-developed automation infrastructure. 14 examples of custom built hardware, software, and workflows were shared. This workshop provided an opportunity for researchers to see user-developed infrastructure in action, learn about how they could integrate these projects into their work, and contribute to discussion about what is needed to advance the state of democratized SDLs. In this perspective, ten contributed examples of user-developed hardware and software from the workshop are highlighted. Despite a diverse array of projects, common motivations for pursuing user-developed infrastructure were cost savings and specification requirements that were unmet by commercially available products. Continuing to advance the state of user-developed automation infrastructure will require commitments to completing high-quality documentation for open-source hardware projects, pathways for materials researchers to learn hardware development skills, and more opportunities for researchers to share their infrastructure advancements, in addition to the scientific advancements that they enable.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.034 | 0.027 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.009 | 0.022 |
| Open science | 0.005 | 0.019 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.008 | 0.004 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".