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.
Under this network and thresholds, no candidate measure survives. The engine is not broken: the theory + data reject the whole menu. Reported range is undefined; do not auto-loosen θ.
[L, U] · method = min/max B*
∅ empty M*
No survivors → no image of β. Inference diagnostics are additive and never loosen θ.
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 | 70f49c7b102be3aea7504a0d7d2e3f0e102ffb6b80d31ff72d6d8fd55b99f6cf |
|---|---|
| package | 3.0.2 |
| scores_hash | 5338e3e4ccec220a8da6b2ab30559ef5e1bb7cc13e99e6a29098cf5f152e8c25 |
| 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 | 0 |
| empty | 1000 (1.000) |
| degenerate | 0 (0.000) |
| band | ∅ |
all replicates empty (or degenerate): band is null; headline [L,U] unchanged
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 | ∅ |
| empty rate | 1.000 |
| degenerate rate | 0.000 |
| measure | p̂m |
|---|---|
| m_trust_general | — |
| m_trust_in_group | — |
| m_trust_out_group | — |
| m_trust_institution | — |
| m_trust_composite | — |
| m_noise | — |
all replicates empty (or degenerate): uncertainty band is null; boundary set empty; admission frequencies null. Heuristic band — not a confidence interval and not a holdout-robustness band.
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 | 0 | yes | — | — |
| 1.0 | 0 | yes | — | — |
| 1.5 | 0 | yes | — | — |
| 2.0 | 0 | yes | — | — |
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 = 0 / 6. Slack rule: admit if sr(m) ≥ −δ for all r.
| measure | status | β(m) | failed restrictions |
|---|---|---|---|
| m_trust_general | rejected | 0.052428 | conv_edu_cell |
| m_trust_in_group | rejected | 0.223931 | conv_edu_cell |
| m_trust_out_group | rejected | 0.211423 | conv_edu_cell |
| m_trust_institution | rejected | 0.284723 | conv_edu_cell |
| m_trust_composite | rejected | 0.317611 | conv_edu_cell |
| m_noise | rejected | 0.014662 | conv_edu_cell |
Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.
| measure | conv_edu_cell | mono_edu_cell |
|---|---|---|
| m_trust_general | -0.176854 | -0.131341 |
| m_trust_in_group | -0.268407 | -0.233353 |
| m_trust_out_group | -0.274989 | -0.224794 |
| m_trust_institution | -0.627369 | -0.552204 |
| m_trust_composite | -0.473703 | -0.414333 |
| m_noise | -0.171912 | -0.119007 |
Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.