COUNTERPHASE / LOCAL SCIENTIFIC ADVERSARY
What did the model learn from evidence it never selected?
Two constrained learning policies. One complete original opportunity ledger. Unselected future outcomes are changed one at a time. A changed decision is a reproducible counterexample.
Cohort SYNTHETIC_BUDGET_20 · 20 T0 opportunities · Offline
Adaptive policy
WITNESSED UNSELECTED LABEL DEPENDENCY
34 challenges run · 0 not tested
- HIDE_UNSELECTED_OUTCOME / 2 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 3 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 4 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 5 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 6 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 7 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 8 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 9 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 12 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 13 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 14 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 15 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 16 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 17 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 18 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
Fixed policy
WITNESSED UNSELECTED LABEL DEPENDENCY
34 challenges run · 0 not tested
- HIDE_UNSELECTED_OUTCOME / 0 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 1 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 3 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 4 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 5 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 6 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 8 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 9 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 10 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 11 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 13 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 14 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 15 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 16 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
- HIDE_UNSELECTED_OUTCOME / 18 — UNSELECTED_LABEL_DEPENDENCY_WITNESSED
Evidence boundary
A passing challenge does not prove the policy never accessed additional labels. Supplied timestamps and selection flags are not independently authenticated. A failing challenge demonstrates dependence on the altered inputs under this local runner, not the causal cause of real-world losses.
Source SHA-256: e7f296f1f8dd9ce9f12cfec515582d50a3d05aab73ae0b97b535b88556142dc4
Policy SHA-256: 442f697824edee0e3cf85a490b506c3bd76d7c3aaea0dbb89b14a9f67152dae2