cvprofiles · construct-validity profile
Admissible measurement set under a stated nomological network, and the image of β on that set. Empty sets and wide ranges are scientific features.
[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_id | 4871250796844cce0317723edc93ad365cd52dc7519c27a33a55f6e89b1baf5b |
|---|---|
| package | 3.0.2 |
| scores_hash | 364c6cdaf6a215cd36b606ba82c02eaafa06ac3258c2c210439a62fb037b5fce |
| network_hash | 55f9b1ac9fa6bd3cbc4bc9f3150b0f2669fe1edfd5beb7bf754f89767f3f8f74 |
| beta_hash | 19fe88c41c4644897cee8c770b625bd57adbae206e1efc2774599c116eacd51e |
| δ | 0.0 |
| seed | 20260814 |
| network | trust_cells_two_resolution |
Units-only Efron resampling; percentile band over non-empty replicates. The headline [L, U] above remains min/max β(M*) on the full sample.
| replicates | 1000 |
|---|---|
| seed | 20260814 |
| quantiles | [0.025, 0.975] |
| non-empty | 1000 |
| empty | 0 (0.000) |
| degenerate | 0 (0.000) |
| band | [0.159691, 0.387414] |
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.
| α | 0.1 |
|---|---|
| κ | 2.0 |
| quantiles | [0.05, 0.95] |
| band | [0.169894, 0.372046] |
| empty rate | 0.000 |
| degenerate rate | 0.000 |
| measure | margin | SE | boundary |
|---|---|---|---|
| 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 |
| measure | p̂m |
|---|---|
| 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.
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*| | empty | L | U |
|---|---|---|---|---|
| 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 |
One pre-data anchor per restriction (hash 07533ac8ce87…). The engine enforces completeness + hash; "pre-data" is a process commitment, not a temporal claim.
| restriction | kind | pre-data | anchor |
|---|---|---|---|
| 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. |
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 |
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 |
Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.