c8850207

By: ValentinHirschi <valentin.hirschi@gmail.com>

record full-orientation joint sampling cost and stability failures

Archive the fixed physical setup, original Samples, native audit and warmed
20-worker timing evidence from 072c9999e. Optimized LMB meets the cost gate;
the joint candidate needs evaluator optimization and one stability diagnosis.
No integration improvement is claimed.

Validation: all archived uncompressed hashes checked; 936 orientations, six
cuts and unchanged saved-state hashes verified; timing subset ratios rebuilt.

User request:
(continue as planned but make sure the time spent in the sampling maps is still quite significantly less than the actual GL638 all-orientation integrand, i.e. it's not crucial to optimize the runtime of the sampling, except if it is somehow comparable to the integrand time; it should be like 10% at the very most, once below that then no need to optimize further).

Timeline