Automatically Capturing Key Features for Predicting Superionic Conductivity of Solid-State Electrolytes Using a Neural Network
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
Solid-state batteries (SSBs) are one of the most promising energy storage technologies due to their low flammability and high energy density compared with currently used liquid-state batteries. The main obstacle to SSB development, however, is the large chemical design space for the solid-state electrolytes (SSEs), as it is significantly time-consuming to screen candidates experimentally or from first-principles simulations. Toward this end, machine learning (ML) offers an efficient strategy. However, current ML models use complex manually created features as inputs based on human intuition, which can introduce human bias, are potentially difficult to obtain for many materials, and can result in a cumbersome feature selection process. This work demonstrates that a neural network-based model utilizing only two simple elemental features (group and period) and one simple structural feature (coordination number) can provide excellent predictive performance comparable to previous manual feature-based studies, while automatically capturing any potential secondary features and reducing the need for human intervention in model training. Such a model is potentially more generalizable than manual feature-based models and can be even applied to other material property predictions, while greatly reducing complexity and training time.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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