Where one study disagrees with what other studies report for the same models, and what we are doing to resolve each case.
These are automatic leads, not findings of error. Each release, a check compares how every study ranks the models it shares with other studies. It flags a study that reverses the order the others agree on, or whose gap to a shared reference model lies well outside theirs. Different tasks, populations or metrics often explain a flag.
A flag never hides a result. Flagged results stay in every table, page and download, marked Contested. A result is withheld only when a reviewer marks it disputed.
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design ranks VESPAl above CARP in 15 of 19 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks CARP above VESPAl in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.
2 papers rank CARP above VESPAl in 10 of their 25 comparisons and VESPAl higher in 15. Of those papers, ProteinGym ranks VESPAl higher on its own (15 of 19).
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design ranks Tranception above VESPAl in 17 of 18 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks VESPAl above Tranception in 6 of 7 comparisons. No other study gives a verdict, so neither is the outlier.
2 papers rank Tranception above VESPAl in 18 of their 26 comparisons and VESPAl higher in 7; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks VESPAl higher on its own (6 of 7).