The full narrative is unavailable.
The original evidence text could not be loaded. Use the source record below; availability of linked files is checked separately.
Open the original HTML fileAll findingsPublished research
Voidly ResearchPublished
How we audited our own shutdown-forecast model and published the embarrassing numbers
Voidly Sentinel publishes three accuracy splits — stratified (inflated 0.98 AUC), time-based (random 0.50), and LOCO median (honest 0.91). We cite the honest number, not the impressive one.
The source record.
Original source links and labels. Linked responses may have changed since publication.