Evaluation registry
Move from development comparison to one-shot evidence without breaking the blind.
Diagnose on frozen development splits, then choose the correct independent design. A pre-existing holdout must predate training; a prospective challenge freezes champion and challenger before any new panel is generated or observed.
Scientific boundary
Every evidence class keeps a different job.
Development metrics diagnose. Independent evidence tests generalization. Neither can silently become activation authority, and every completed result is recomputed from immutable custody records.
Registered matrices
0
immutable Program records
Currently reverified
0
archive bytes checked at read time
Frozen datasets
0
content-addressed package identities
Activation eligible
0
requires independent blind evidence
No baseline matrix is loaded for this Program.
Start with an authorized, frozen dataset package. Run the CPU baseline evaluator without changing its split, package the complete output, then verify and register it here. Metrics are intentionally absent until real evidence exists.