SITE HETEROGENEITY - 0.2-SH1

One score.
More than one site.

A pooled survival estimate can look stable while one field operation supplies nearly every household. WANTED WILD now requires at least three substantive sites, caps any site at half the cohort, reproduces W within each site, and removes each site in turn.

3+SUBSTANTIVE SITES
≤50%MAX SITE SHARE
3+ENVIRONMENTS / SITE
0RANKING WEIGHT
01 / POOLED-SCORE DEFENSE

Spread the evidence.
Expose the dependence.

Topology is a certification gate. Site-specific outcomes are public diagnostics and never become a second score or tiebreaker.

SH1FROZEN DESIGN

Define sites before outcomes exist.

REQUIRED
SH2MULTI-SITE SUPPORT

At least three substantive sites.

REQUIRED
SH3BOUND ENDPOINTS

One opaque site per environment.

REQUIRED
SH4POOLED IDENTITY

Never replace or reweight W.

REQUIRED
SH5SITE DISCLOSURE

Report W or null by site.

REQUIRED
SH6SITE-OUT SENSITIVITY

Remove each site in turn.

REQUIRED
SH7INDEPENDENT AUDIT

Bind assignments and reproduction.

REQUIRED
02 / SAME ESTIMATOR

Partition the rows.
Do not move the goalposts.

Every site uses the same A2 event, censoring, tie, horizon, and refusal rules. Unsupported site tails remain null. The official pooled W stays the unweighted environment-level estimate.

DOMINANCE + SENSITIVITYmaxs ns/N ≤ 0.50
Δsite-out = maxs|W-s − W|

Passing limits concentration. It does not impose a performance threshold on site-specific W or its range.

03 / PUBLIC TRACE

Show where
the score moves.

Opaque site IDs protect participants while preserving every site count, share, identifiable estimate, unsupported tail, and site-exclusion result.

TOPOLOGY

Site count, smallest N, and maximum cohort share.

WITHIN SITE

W and S(10K), or null when the tail is unsupported.

SITE EXCLUSION

Complete leave-one-site-out table and maximum absolute shift.

BOUNDARY

No geographic, dwelling, cultural, or population generalization claim.

04 / LOCAL VERIFIER

Bind every site.
Recompute every view.

The verifier runs locally against opaque site assignments and endpoint rows. It checks prospective design, topology, pooled identity, site results, site-exclusion sensitivity, digests, and independent attestation.

LOCAL SITE HETEROGENEITY VERIFIERPROFILE / 0.2-SH1
SITE HETEROGENEITYPASSEDAll seven multi-site gates pass.
POOLED W87.500
SITES3
MAX SITE SHARE33.3%
MAX SITE-OUT SHIFT3.125
site_alpha90.625N=8 · 33.3%
site_beta90.625N=8 · 33.3%
site_gamma81.250N=8 · 33.3%
SH1
FROZEN SITE DESIGN

Site definition and dominance limits were frozen before benchmark activity.

PASS
SH2
MULTI-SITE SUPPORT

At least three substantive sites contribute without one site exceeding half the cohort.

PASS
SH3
BOUND ENDPOINT ROWS

Every unique environment maps to one opaque site and a rankable A2 endpoint.

PASS
SH4
POOLED SCORE IDENTITY

The pooled W and S(10K) reproduce without reweighting or score substitution.

PASS
SH5
SITE-SPECIFIC DISCLOSURE

Every site-specific W is reported when identifiable and null otherwise.

PASS
SH6
LEAVE-ONE-SITE-OUT

Every site exclusion is recomputed and maximum pooled-score sensitivity is disclosed.

PASS
SH7
BOUND INDEPENDENT AUDIT

Controlled site assignments and the reproduction log are digest-bound and independently attested.

PASS
HETEROGENEITY != RANK

W alone orders eligible WILD entries. Site range, dominance, and leave-one-site-out shift are mandatory public diagnostics and forbidden tiebreakers.

OPEN LEADERBOARD ->