# H04_E_MECHANICAL_CONFOUND_RESULT_v0_1

**Confound freeze:** `H04_E_MECHANICAL_CONFOUND_FREEZE_v0_1` sha `bcd6867f5c4fdac9ad26d3ab1daf5b4de0bb311aac0efff3e255f21a238c274d`  
**Result JSON sha256:** `c91e7e426c6d26621779d41df5f64d037db26562f3920b3dd13ed2cbc2cd697b`  
**Parent H04-E result sha:** `a268ee06fe3536d401e117a5ff83ad49f56b2761a5cae4d75688425669a84abb`  
**Hub job:** `77356229-193e-4693-a90c-cae8dcb0bc4a`  
**Created:** 2026-09-13T23:11:14Z

## STATUS
EXPLORATORY · VINTAGE UNVERIFIED/INCOMPLETE · CLAIM_STRENGTH LOW · CAPITAL_USE PROHIBITED · MODEL_CHANGE NO

## Primary check C1_NESTED_MECH_RAW_DELTA
Same sample as H04-E: Development N=59 · Holdout N=81

| Model | RMSE | MAE | DirAcc |
|-------|------|-----|--------|
| A0 (H04-E baseline) | 16.508261 | 13.095205 | 0.4815 |
| A_mech (A0 + raw mean Δ) | 10.607395 | 6.800874 | 0.8519 |
| B_vs_mech (A_mech + surprise) | 10.623855 | 6.990181 | 0.8148 |

### Primary metric (decision)
- Incremental % RMSE improvement B_vs_mech over A_mech: **-0.1552%**
- Threshold: **5.0%**
- Surprise coef | mechanical: **-0.002332**
- Mech coef in A_mech: **0.004233**

### Diagnostics (not decision)
- A0 → A_mech % improvement: **35.7449%** (raw WPSR delta alone)
- A0 → B_original % (H04-E replay): **34.2543%**

## Disposition
# **MECHANICAL**

Claim framing: **DOWNGRADED_MECHANICAL**

H04-E mechanical confound C1: incremental holdout RMSE improvement of surprise over A0+raw_mean_delta = -0.1552% (bar 5%). A_mech RMSE=10.6074, B_vs_mech RMSE=10.6239. Diagnostic: raw delta alone vs A0 improves 35.74%. Disposition MECHANICAL. CLAIM_STRENGTH LOW; capital prohibited; not a validated edge.

## Caveats
- Still not first-print vintage; STEO dates mixed PARSED/SCHEDULE_PROXY
- Collinearity between raw Δ and surprise is expected; that is the point of the screen
- CAPITAL PROHIBITED · NOT a validated edge · Explore the click only