DOME preprint v2

Author: sfragkoul

_bibliography/references.bib

@@ -1801,6 +1801,20 @@ @inproceedings{BloodASH_2019a
 %		       Other (Slides/Datasets/Short articles/Preprints)
 %==========================================================
 
+@article {Farrell2026.04.16.718888,
+	author = {Farrell, Gavin and Attafi, Omar Abdelghani and Fragkouli, Styliani-Christina and Heredia, Ignacio and Fern{\'a}ndez Tobias, Saul and Harrison, Melissa and Hermjakob, Henning and Jeffryes, Matt and Mehdiabadi, Mahta and {\'O}bregon Ruiz, Marta and Pearce, Matt and Pechlivanis, Nikos and Quaglia, Federica and L{\'o}pez Garc{\'\i}a, Alvaro and Psomopoulos, Fotis and Tosatto, Silvio C.E.},
+	title = {DOME Copilot: A resource to automate transparent reporting of artificial intelligence methods},
+	elocation-id = {2026.04.16.718888},
+	year = {2026},
+	doi = {10.64898/2026.04.16.718888},
+	publisher = {Cold Spring Harbor Laboratory},
+	abstract = {Artificial intelligence (AI) methods are transforming life science research and witnessing unprecedented adoption across literature. While AI is driving impactful discoveries, this rapid growth in application has inundated researchers with poorly described models and datasets which lack transparency, impeding reusability and eroding trust. The DOME Recommendations aimed to address this issue and established structured reporting guidelines to standardize AI methodology descriptions. However, the need to manually create these comprehensive disclosures imposed a major bottleneck, requiring substantial effort from authors to comply. To bridge this gap, we present DOME Copilot, an open-source, easily deployable system that automates the generation of transparent AI methodology reports supplementing publications. Evaluated against a benchmark of human-created annotations, DOME Copilot was determined to match or exceed manual annotation quality across the majority of reporting fields while reducing the creation time from hours to minutes. Ultimately, the system provides a novel and scalable solution to restore confidence in complex life science AI method publications.Competing Interest StatementThe authors have declared no competing interest.},
+	URL = {https://www.biorxiv.org/content/early/2026/07/24/2026.04.16.718888},
+	eprint = {https://www.biorxiv.org/content/early/2026/07/24/2026.04.16.718888.full.pdf},
+	journal = {bioRxiv}
+}
+
+
 @misc{morsy_2026, 
 title={The FAIR guiding principles for training materials}, 
 url={osf.io/preprints/metaarxiv/8tzq5_v1},