Commit History
18 days ago
-
Document paused Decision Index 0.3 benchmark results
Verified signaturefeed4bd
19 days ago
-
Add MPS ARC-Easy Decision Index comparison
Verified signaturebb81db2 -
Document WinoGrande Decision Index 0.3 single-benchmark result
Verified signature192c1fb -
Improve model card and calibration visual
Verified signature91b3b71 -
Document held-out temperature calibration
Verified signature8d152d5 -
Publish evaluated stage-16 Safetensors checkpoint and model card
Verified signature2fa7a93 -
initial commit
Verified signaturef1c470d