The AI told them that % and nobody questioned it :)

Easy. 14÷(14+1+8) = 0.608695652 Oops.

Maybe they didn't include the missed prediction.

14÷(14+8) = 0.636363636

Maybe they rounded up. A lot.

The article is so information-lite that a possibility I wouldn't rule out was that of 20 earthquakes in the trial, it made predictions for 14 earthquakes that were close enough to count as a success criterion, it made predictions for 5 earthquakes that were substantially off in location and/or magnitude but not entirely misses, 1 earthquake that it missed entirely, and 8 more earthquakes that it predicted that didn't occur.

~61% is what that sounds like.

Even lower it you take the f1 score...

Should be 14/15 = 93.3%

Because: “of earthquakes”