Magdalena Skipper

magdalenaskipper.bsky.social

07 August 2025 12:10

A rubber duck has made it to our cover! Why? It’s the latest tool to help solve a formidable challenge - design an adhesive that remain effective in wet environments. @nature.com 🧪 Further details here (spoiler - inspiration comes from biology) www.nature.com/articles/s41...

Ole Goltermann

olegolt.bsky.social

05 August 2025 12:59

Unfortunately, their reply does not address our first concern. It fails to explain why they report an AUC of 1.0 for a validation set, which by definition is not a proper validation set, and why a random seed of 23 was chosen for this analysis.

Russ Poldrack

russpoldrack.org

23 July 2025 08:18

Any time a paper reports an AUC of 1.0 on test data, my hackles are raised. This commentary by @olegolt.bsky.social @tspisak.bsky.social @christianbuchel.bsky.social nicely dissects problems with a recently reported "biomarker" for pain.

Ole Goltermann

olegolt.bsky.social

23 July 2025 07:42

All our code, including further comments are available here: github.com/olegolt/PAF_... (13/13)

Ole Goltermann

olegolt.bsky.social

23 July 2025 07:42

Our reanalysis showed that 99.6% of all possible subsets yield lower AUCs than the reported 1.0 (see Figure 1). A bit surprising to us, appropriate performance metrics were already available in their own code: average cross-validation AUC (0.65) and locked model AUC (0.73). 👇 7/13