Benchmarking the Discovery Engine
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916819928875008 |
|---|---|
| author | Foxabbott, Jack Tagade, Arush Cusick, Andrew McCorkell, Robbie McKee-Reid, Leo Patel, Jugal Rumbelow, Jamie Rumbelow, Jessica Shams, Zohreh |
| author_facet | Foxabbott, Jack Tagade, Arush Cusick, Andrew McCorkell, Robbie McKee-Reid, Leo Patel, Jugal Rumbelow, Jamie Rumbelow, Jessica Shams, Zohreh |
| contents | The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and robust scientific insight across diverse datasets. In this paper, we benchmark the Discovery Engine against five recent peer-reviewed scientific publications applying machine learning across medicine, materials science, social science, and environmental science. In each case, the Discovery Engine matches or exceeds prior predictive performance while also generating deeper, more actionable insights through rich interpretability artefacts. These results demonstrate its potential as a new standard for automated, interpretable scientific modelling that enables complex knowledge discovery from data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking the Discovery Engine Foxabbott, Jack Tagade, Arush Cusick, Andrew McCorkell, Robbie McKee-Reid, Leo Patel, Jugal Rumbelow, Jamie Rumbelow, Jessica Shams, Zohreh Machine Learning I.2.6; I.2.3; I.5.1; H.2.8; J.2; J.3; J.4 The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and robust scientific insight across diverse datasets. In this paper, we benchmark the Discovery Engine against five recent peer-reviewed scientific publications applying machine learning across medicine, materials science, social science, and environmental science. In each case, the Discovery Engine matches or exceeds prior predictive performance while also generating deeper, more actionable insights through rich interpretability artefacts. These results demonstrate its potential as a new standard for automated, interpretable scientific modelling that enables complex knowledge discovery from data. |
| title | Benchmarking the Discovery Engine |
| topic | Machine Learning I.2.6; I.2.3; I.5.1; H.2.8; J.2; J.3; J.4 |
| url | https://arxiv.org/abs/2507.00964 |