cvprofiles · construct-validity profile

Trust — cells

Admissible measurement set under a stated nomological network, and the image of β on that set. Empty sets and wide ranges are scientific features.

Construct-identified range

[L, U] · method = min/max B*

[0.250656, 0.317003]

Width = 0.066348 · 3 survivors · bootstrap percentile band = [0.159691, 0.387414]

Target β = corr_y on outcome gps_trust_cell. Range uses only measures in M*; rejected β values are shown below but never enter [L,U].

Run freeze

run_id4871250796844cce0317723edc93ad365cd52dc7519c27a33a55f6e89b1baf5b
package3.0.2
scores_hash364c6cdaf6a215cd36b606ba82c02eaafa06ac3258c2c210439a62fb037b5fce
network_hash55f9b1ac9fa6bd3cbc4bc9f3150b0f2669fe1edfd5beb7bf754f89767f3f8f74
beta_hash19fe88c41c4644897cee8c770b625bd57adbae206e1efc2774599c116eacd51e
δ0.0
seed20260814
networktrust_cells_two_resolution

Bootstrap inference · additive to headline range

Units-only Efron resampling; percentile band over non-empty replicates. The headline [L, U] above remains min/max β(M*) on the full sample.

replicates1000
seed20260814
quantiles[0.025, 0.975]
non-empty1000
empty0 (0.000)
degenerate0 (0.000)
band[0.159691, 0.387414]

Uncertainty band · additive to headline range

Per-side α/2 quantiles over non-empty bootstrap replicates (α = 0.1). Heuristic band — not a confidence interval, not a holdout-robustness band. The headline [L, U] above remains min/max β(M*) on the full sample.

α0.1
κ2.0
quantiles[0.05, 0.95]
band[0.169894, 0.372046]
empty rate0.000
degenerate rate0.000

Boundary attribution · |margin| ≤ κ·SE

measuremarginSEboundary
m_trust_general 0.245799 0.038439 no
m_trust_in_group 0.042867 0.036143 yes
m_trust_out_group 0.205031 0.036730 no
m_trust_institution -0.508458 0.037005 no
m_trust_composite -0.118671 0.038503 no
m_noise -0.139257 0.046634 no

Admission frequency p̂m

measurep̂m
m_trust_general 1.000
m_trust_in_group 0.882
m_trust_out_group 1.000
m_trust_institution 0.000
m_trust_composite 0.004
m_noise 0.001

Heuristic uncertainty band over non-empty bootstrap replicates (selection uncertainty on the pooled sample; holdout verdict is a full-sample point finding outside the band). Not a confidence interval; not a holdout-robustness band. Boundary attribution: |margin_m| <= kappa * SE_m.

θ-grid sensitivity · diagnostic viewport

λ scales threshold magnitudes only. λ is never auto-selected; the headline is always λ=1.0. This grid is not part of the freeze preimage.

λ|M*|emptyLU
0.5 3 no 0.250656 0.317003
1.0 3 no 0.250656 0.317003
1.5 2 no 0.250656 0.251731
2.0 2 no 0.250656 0.251731

θ-anchors · pre-data audit

One pre-data anchor per restriction (hash 07533ac8ce87…). The engine enforces completeness + hash; "pre-data" is a process commitment, not a temporal claim.

restrictionkindpre-dataanchor
conv_edu_cell literature yes falk2018_table_v — Same education implication applied within country (cell means). θ=0.20.
mono_edu_cell literature yes falk2018_table_v — Leftover within-country rank-monotone education restriction. θ=0.15.

Menu admission

M* size = 3 / 6. Slack rule: admit if sr(m) ≥ −δ for all r.

measure status β(m) failed restrictions
m_trust_general admissible 0.251731 —
m_trust_in_group admissible 0.317003 —
m_trust_out_group admissible 0.250656 —
m_trust_institution rejected 0.420264 conv_edu_cell
m_trust_composite rejected 0.449102 conv_edu_cell
m_noise rejected 0.049932 conv_edu_cell

Slack matrix sr(m)

Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.

measure conv_edu_cell mono_edu_cell
m_trust_general 0.245799 0.321203
m_trust_in_group 0.042867 0.073163
m_trust_out_group 0.205031 0.209837
m_trust_institution -0.508458 -0.432085
m_trust_composite -0.118671 -0.076046
m_noise -0.139257 -0.064095

Network (researcher-owned)

Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.