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*
[0.244910, 0.244910]
Width = 0.000000 · point-ID · bootstrap percentile band = [0.157887, 0.348094]
Target β = corr_y on outcome gps_patience_cell. Range uses only measures in M*; rejected β values are shown below but never enter [L,U].
| run_id | 587664d7ff0fde4a67bf4016c47d2c1b71c502a20cff8a13597fedf5202cbe2b |
|---|---|
| package | 3.0.2 |
| scores_hash | 542ac41e4c60ab0c1dc2bc311c682779d084de37dae77a6dc418981f120c2742 |
| network_hash | 1ed753b6c1ed159c4451ced75d2c8dba44318ce91b4f30dfbfb234d1dff7caf4 |
| beta_hash | 93ecc94543944de5860e399f0b91f9f1c5038e5b4d418e5f3444d3b0a8bc23c7 |
| δ | 0.0 |
| seed | 20260814 |
| network | patience_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 | 830 |
| empty | 170 (0.170) |
| degenerate | 0 (0.000) |
| band | [0.157887, 0.348094] |
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 | [0.174387, 0.334673] |
| empty rate | 0.170 |
| degenerate rate | 0.000 |
| measure | margin | SE | boundary |
|---|---|---|---|
| m_wvs_q13 | 0.051086 | 0.038993 | yes |
| m_wvs_q14 | -0.564248 | 0.043948 | no |
| m_composite | -0.249511 | 0.049958 | no |
| m_noise | -0.230693 | 0.045301 | no |
| measure | p̂m |
|---|---|
| m_wvs_q13 | 1.000 |
| m_wvs_q14 | 0.000 |
| m_composite | 0.000 |
| m_noise | 0.000 |
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 | 1 | no | 0.244910 | 0.244910 |
| 1.0 | 1 | no | 0.244910 | 0.244910 |
| 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 = 1 / 4. Slack rule: admit if sr(m) ≥ −δ for all r.
| measure | status | β(m) | failed restrictions |
|---|---|---|---|
| m_wvs_q13 | admissible | 0.244910 | — |
| m_wvs_q14 | rejected | -0.325797 | conv_edu_cell |
| m_composite | rejected | -0.026645 | conv_edu_cell |
| m_noise | rejected | -0.002776 | conv_edu_cell |
Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.
| measure | conv_edu_cell | mono_edu_cell |
|---|---|---|
| m_wvs_q13 | 0.051086 | 0.060120 |
| m_wvs_q14 | -0.564248 | -0.498965 |
| m_composite | -0.249511 | -0.221653 |
| m_noise | -0.230693 | -0.165338 |
Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.