DELFI: A computer oracle for recommending density functionals for excited states calculations
Bibliographic record
Abstract
Density functional theory (DFT) is known as the workhorse of computational quantum chemistry. One of its main limitations, if not the main one, is that choosing the right functional to employ is a non-trivial task left for human experts. The choice is particularly hard for excited states calculations, when using the time-dependent formulation of DFT (TD-DFT). This is not only due to the approximations and limitations of the method, but also because the photophysical properties of a molecule are defined by a manifold of states that all need to be properly described in a balanced manner to obtain an accurate photochemical picture. This includes not only the relative energy of the states, but also capturing the correct character, order and intensity of the transitions. In this work, we developed a scoring system to quantitatively define the accuracy of an excited states calculation by simultaneously considering at the same time all these properties of a manifold of states. The scoring system is generalizable to any level of theory, we here applied it to a large dataset of organic molecules, calculating 38 scores for as many common functionals of different type and rung, against a higher accuracy method for a total of more than 820.000 single point calculations. The results of these calculations are collected in a database that we released and made it open, providing 4 million datapoints to be used by the community for future applications. We used the scores we extrapolated to train a graph attention neural network that is used to predict the 38 scores for molecules represented as 2D graphs. We call this oracle DELFI (Data-driven EvaLuation of Functionals by Inference), which can be used to quickly screen and predict the ranking of functionals to calculate optical properties of organic molecules. A corresponding web application allows to easily run DELFI and analyze the results, alleviating the hurdle of choosing the right functional for TD-DFT calculations.
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 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 | 0.001 |
| 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 | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".