Supporting data for "Multi-head committees enable direct uncertainty prediction for atomistic foundation models"
Fuente:
Zenodo
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Recurso digital |
| Publié: |
Zenodo
2025
|
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901305757270016 |
|---|---|
| author | Beck, Hubert Simko, Pavol |
| author_facet | Beck, Hubert Simko, Pavol |
| contents | <p>The data is sorted by the respective datasets that were used to train and analyze the models. These datasets for custom-made models are 3BPA, water, and rMD17. There is a separate directory for the foundation model. The directories contain the training datasets, the scripts used to create the training sets, training scripts, and the trained models.</p> <p><strong>3BPA:</strong> Contains directories for different training set sizes. Most work was done on the 100-strucutre training set contained in the `trainset_100` directory. This directory also contains sub-directories that were used for work in the supplementary material, such as committees without training set subsampling.</p> <p><strong>water:</strong> Contains the training, validation, and test sets for the analysis of bulk liquid water.</p> <p><strong>rMD17: </strong>The directory `full_trainset` contains the material used for the work found in the main manuscript. Additionally, there are directories `wo_*`, which contain the material for the models where one molecule was excluded. The analysis of these models can be found in the supplementary material.</p> <p><strong>foundation: </strong>The most important directory of this part is `qbc/dataset_8000`, containing the QbC-selected reduced training dataset of MPtrj and a trained multihead committee model with and without the original pre-trained head. Additionally, there are models trained on only the 1000 structures selected first by the QbC as well as models trained on randomly selected structures and the structures in the MPtrj dataset with the maximum mean force.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17829635 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Supporting data for "Multi-head committees enable direct uncertainty prediction for atomistic foundation models" Beck, Hubert Simko, Pavol <p>The data is sorted by the respective datasets that were used to train and analyze the models. These datasets for custom-made models are 3BPA, water, and rMD17. There is a separate directory for the foundation model. The directories contain the training datasets, the scripts used to create the training sets, training scripts, and the trained models.</p> <p><strong>3BPA:</strong> Contains directories for different training set sizes. Most work was done on the 100-strucutre training set contained in the `trainset_100` directory. This directory also contains sub-directories that were used for work in the supplementary material, such as committees without training set subsampling.</p> <p><strong>water:</strong> Contains the training, validation, and test sets for the analysis of bulk liquid water.</p> <p><strong>rMD17: </strong>The directory `full_trainset` contains the material used for the work found in the main manuscript. Additionally, there are directories `wo_*`, which contain the material for the models where one molecule was excluded. The analysis of these models can be found in the supplementary material.</p> <p><strong>foundation: </strong>The most important directory of this part is `qbc/dataset_8000`, containing the QbC-selected reduced training dataset of MPtrj and a trained multihead committee model with and without the original pre-trained head. Additionally, there are models trained on only the 1000 structures selected first by the QbC as well as models trained on randomly selected structures and the structures in the MPtrj dataset with the maximum mean force.</p> |
| title | Supporting data for "Multi-head committees enable direct uncertainty prediction for atomistic foundation models" |
| url | https://doi.org/10.5281/zenodo.17829635 |