All six complete covers pass the original width target
All 48 regions passed. All six complete case covers meet the original twofold-width target in north, east and height. The saved-only rebuild took 258.34 seconds and used 336 report merges, with no integration or aircraft fit.
| Generated case / processing | North width | East width | Height width | Target |
|---|---|---|---|---|
| Specified-field globe / zero removal | 0.9558 m | 1.3816 m | 0.7675 m | Pass |
| Specified-field globe / profiled removal | 0.9872 m | 1.3923 m | 0.8008 m | Pass |
| Zero-field globe / zero removal | 0.7666 m | 0.7998 m | 0.5658 m | Pass |
| Zero-field globe / profiled removal | 0.8485 m | 0.8800 m | 0.6451 m | Pass |
| Flat disc / zero removal | 0.6459 m | 0.2002 m | 0.3924 m | Pass |
| Flat disc / profiled removal | 0.7440 m | 0.2370 m | 0.4865 m | Pass |
These are known-answer generated histories covering each physical candidate and both processing assumptions. They qualify the prediction calculation on the existing short example. The aircraft findings remain 53 globe preferences, zero flat preferences and zero unresolved comparisons.
What resolved the earlier failures
The serial execution recipe completed twelve missing future certificates while retaining the unchanged algorithm and 120-second per-bound limit. Their earlier timeouts remain recorded. The new rebuild reused completed training reports, checked all three source studies' provenance, and independently audited the training constraints and future supports.
Every case includes all eight fresh regions. Complete fresh covers are combined with the earlier complete 192-box covers; both ranges remain in the result artifact. No inherited-only fallback or partial successful subset qualifies this matrix. The two formerly failing east widths now pass without changing physical bounds, error allowances or the target.
What remains before aircraft prediction fits
This check predicts at 7.2 seconds. It does not establish useful uncertainty over four- to eleven-minute recordings. The method still needs recording-length qualification and an adequate error model, including receiver and accumulated inertial errors. Exact component arithmetic checks also remain distinct from a whole-program floating-execution certificate.
The next plan preserves the earlier four-minute failures and requires a costed new feasibility study. No new aircraft fit, confidence level or empirical model preference follows from this software gate.
Verified results and accounting · Frozen scope · Error assumptions.