no code implementations • 2 Feb 2024 • Jeremy Wayland, Corinna Coupette, Bastian Rieck
Echoing recent calls to counter reliability and robustness concerns in machine learning via multiverse analysis, we present PRESTO, a principled framework for mapping the multiverse of machine-learning models that rely on latent representations.
no code implementations • 1 Jun 2023 • Bastian Rieck, Corinna Coupette
With machine learning conferences growing ever larger, and reviewing processes becoming increasingly elaborate, more data-driven insights into their workings are required.
1 code implementation • 21 Oct 2022 • Corinna Coupette, Sebastian Dalleiger, Bastian Rieck
Bridging geometry and topology, curvature is a powerful and expressive invariant.
2 code implementations • 16 Jun 2022 • Corinna Coupette, Jilles Vreeken, Bastian Rieck
We introduce Hyperbard, a dataset of diverse relational data representations derived from Shakespeare's plays.
no code implementations • 19 Apr 2022 • Corinna Coupette, Dirk Hartung
We introduce seven foundational principles for creating a culture of constructive criticism in computational legal studies.
no code implementations • 16 Dec 2021 • Corinna Coupette, Sebastian Dalleiger, Jilles Vreeken
How does neural connectivity in autistic children differ from neural connectivity in healthy children or autistic youths?
no code implementations • 15 Oct 2021 • Corinna Coupette, Dirk Hartung, Janis Beckedorf, Maximilian Böther, Daniel Martin Katz
Building on the computer science concept of code smells, we initiate the study of law smells, i. e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law.
no code implementations • 2 Oct 2021 • Corinna Coupette, Jyotsna Singh, Holger Spamann
Textual redundancy is one of the main challenges to ensuring that legal texts remain comprehensible and maintainable.
no code implementations • 29 May 2021 • Corinna Coupette, Jilles Vreeken
We formalize this problem as a model selection task using the Minimum Description Length principle, capturing the similarity of the input graphs in a common model and the differences between them in transformations to individual models.