Tree — 07

metrics/2

data/1

Evaluation

What a number on a leaderboard is actually measuring, and the two failure modes that dominate: the benchmark leaked into pretraining, or the difference between two systems is inside the noise.

Three entries, none of them stubs.

Entries

Contamination Detection

n-gram and canary overlap tests between benchmark and pretraining data.

Elo / Bradley-Terry Scoring

Latent-strength model fitted to pairwise preference outcomes.

Exponentiated mean negative log-likelihood over a held-out corpus.