eval-harness

reference

gold/scifact_40 gold

Promoted as gold: the yardstick a decision rests on.
Promoted from person the dataset's authors, 2026-09-28: promoted before labels existed (0.6.0): its tier was given when it was made

01what it is

tier
gold
dataset
scifact_40
promoted from
person the dataset's authors
why
promoted before labels existed (0.6.0): its tier was given when it was made
items
40
created
2026-09-28T14:59:25Z

02scored against it · 0

No arm is scored against it yet.