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*
[0.106829, 0.481254]
Width = 0.374424 · 5 survivors · bootstrap percentile band = [-0.039153, 0.730078]
Target β = ols_coef on outcome log_gdp_pc. Range uses only measures in M*; rejected β values are shown below but never enter [L,U].
| run_id | de21a795a0dee6202efdf3928900da59ba74c174ed5ba48124c7e28adb5806a2 |
|---|---|
| package | 3.0.2 |
| scores_hash | 0b115ce85abef8fdd43764332a20f660534099656635cc553d279bc5f6254860 |
| network_hash | 27490da9292c755027cb295162238dbfda45e5f032d037775bf1d10e21b951e4 |
| beta_hash | 40040c2105c1d9b34e212dddd8ca9487fdb315d4db2ebee0ebaf29129df5cafe |
| δ | 0.0 |
| seed | 20260814 |
| network | trust_country_llm_extension |
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 | 999 |
| empty | 1 (0.001) |
| degenerate | 0 (0.000) |
| band | [-0.039153, 0.730078] |
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 | [-0.016141, 0.698761] |
| empty rate | 0.001 |
| degenerate rate | 0.000 |
| measure | margin | SE | boundary |
|---|---|---|---|
| m_gps_trust | -0.197064 | 0.156197 | yes |
| m_trust_general | 0.306865 | 0.121647 | no |
| m_trust_in_group | 0.097667 | 0.116052 | yes |
| m_trust_out_group | 0.219973 | 0.114168 | yes |
| m_trust_institution | -0.562602 | 0.125151 | no |
| m_trust_composite | -0.051991 | 0.121806 | yes |
| m_llm_trust_llama | 0.196624 | 0.132026 | yes |
| m_llm_trust_phi | -0.158092 | 0.188466 | yes |
| m_noise | -0.373876 | 0.157017 | no |
| measure | p̂m |
|---|---|
| m_gps_trust | 0.127 |
| m_trust_general | 0.997 |
| m_trust_in_group | 0.909 |
| m_trust_out_group | 0.945 |
| m_trust_institution | 0.001 |
| m_trust_composite | 0.788 |
| m_llm_trust_llama | 0.901 |
| m_llm_trust_phi | 0.167 |
| m_noise | 0.007 |
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 | 5 | no | 0.106829 | 0.481254 |
| 1.0 | 5 | no | 0.106829 | 0.481254 |
| 1.5 | 4 | no | 0.191812 | 0.481254 |
| 2.0 | 3 | no | 0.266456 | 0.481254 |
One pre-data anchor per restriction (hash 68e155f6775d…). The engine enforces completeness + hash; "pre-data" is a process commitment, not a temporal claim.
| restriction | kind | pre-data | anchor |
|---|---|---|---|
| conv_rule_of_law | literature | yes | aghion2010_h5 — Trust–institutions correlations typically ≥0.4 (Aghion, Algan, Cahuc, Shleifer 2010). H5 historical floor 0.30. |
| disc_gini | literature | yes | bjornskov2008_h5 — Bjørnskov 2008: negative trust–inequality relationship. H5 historical θ=0.10 on corr_sign. |
| conv_edu_hold | literature | yes | falk2018_table_v — Falk et al. 2018 Table V: trust increases with cognitive ability in almost all countries. Leftover country-level education bar θ=0.20. |
M* size = 5 / 9. Slack rule: admit if sr(m) ≥ −δ for all r.
| measure | status | β(m) | failed restrictions |
|---|---|---|---|
| m_gps_trust | rejected | 0.109023 | conv_rule_of_law |
| m_trust_general | admissible | 0.390598 | — |
| m_trust_in_group | admissible | 0.191812 | — |
| m_trust_out_group | admissible | 0.266456 | — |
| m_trust_institution | rejected | -0.092285 | conv_rule_of_law |
| m_trust_composite | admissible | 0.106829 | — |
| m_llm_trust_llama | admissible | 0.481254 | — |
| m_llm_trust_phi | rejected | 0.386442 | disc_gini |
| m_noise | rejected | 0.028351 | conv_rule_of_law, disc_gini |
Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.
| measure | conv_rule_of_law | disc_gini | conv_edu_hold |
|---|---|---|---|
| m_gps_trust | -0.176415 | 0.003543 | -0.197064 |
| m_trust_general | 0.404767 | 0.421874 | 0.306865 |
| m_trust_in_group | 0.182494 | 0.509629 | 0.097667 |
| m_trust_out_group | 0.358501 | 0.219973 | 0.328627 |
| m_trust_institution | -0.424613 | 0.175068 | -0.562602 |
| m_trust_composite | 0.104768 | 0.407739 | -0.051991 |
| m_llm_trust_llama | 0.475050 | 0.196624 | 0.221417 |
| m_llm_trust_phi | 0.361173 | -0.158092 | 0.050590 |
| m_noise | -0.373876 | -0.004827 | -0.101694 |
Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.