Framework Science and Technology Facilities Council 2023
SyMDis
Sample-efficient symbolic-learning optimisation method that discovers near-optimal materials from large databases and learns interpretable rules.[13]
Workflow level n/a Source: Preprint (not peer-reviewed)
Research applicability
Sample-efficient symbolic-learning optimisation method that discovers near-optimal materials from large databases and learns interpretable rules.[13]
Getting started
Review the paper (arXiv:2312.11487) for the method and evaluation protocol; availability not verified.
Maintenance
Maintenance status not independently audited.
License
Not independently audited.
Workflow & human oversight
Resource-level classification is intentionally unspecified; instantiated workflows may differ. Humans set objectives and validate results.
Workflow level is not an evidence score; higher is not better evidence.
Approach
Learns symbolic rules for material selection over a large database search task; rules generalise to unseen datasets and are intended to aid physical and chemical verification.[13]
Outcomes (as reported by the originating team)
Author-reported: performance comparable to a state-of-the-art optimiser while learning interpretable rules; high-performing candidates returned on unseen datasets in a zero-shot evaluation.
Limitations
Preprint; no code availability verified; not independently reproduced.
Reproducibility
Live source checks 2026-10-16: arXiv:2312.11487. No claimed outcome reproduced.
Adoption requirements
A database of candidate materials with a scoring or simulation function; no packaged implementation verified.
Comments
No comments yet.
Add a comment
Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.