← Back

Validation Lab

Walk-forward validation, holdout review, and promotion readiness
Total Runs
6
Completed
5
Needs Review
3
Promote
0

Validation Runs

Stored research runs for challenger vs baseline comparison
Name Status Models Primary Metric Windows Holdout Delta Recommendation Created
Campaign Minutes Calibration Sprint 01 Run 6 Completed
Baseline: structured-0010-0003
Challenger: structured-0015-0003
MinutesMae RollingWithHoldout
2 eval + 1 holdout
0.33 Reject
2026-03-24 13:13
View
Campaign Minutes Calibration Sprint 01 Run 5 Completed
Baseline: structured-0010-0003
Challenger: structured-0014-0003
MinutesMae RollingWithHoldout
2 eval + 1 holdout
0.33 Reject
2026-03-24 11:36
View
Validate Active random-0007-0006 vs Challenger 45 Completed
Baseline: random-0007-0006
Challenger: structured-0010-0003
MinutesMae RollingWithHoldout
3 eval + 1 holdout
-0.20 Reject
2026-03-11 07:52
View
Validate Active v1 vs Challenger 22 Completed
Baseline: v1
Challenger: random-0007-0006
PraMae RollingWithHoldout
4 eval + 1 holdout
-0.21 NeedsReview
2026-03-09 17:41
View
Validate Active v1 vs Challenger 22 Completed
Baseline: v1
Challenger: random-0007-0006
PraMae RollingWithHoldout
4 eval + 1 holdout
-0.21 NeedsReview
2026-03-09 17:08
View
Validate Active v1 vs Challenger 22 Running
Baseline: v1
Challenger: random-0007-0006
PraMae RollingWithHoldout
4 eval + 1 holdout
NeedsReview
2026-03-09 16:58
View