Blood manifest: 46 samples
Loaded 21,729,756 rows from 46 blood samples in 25.6s
GC reference: 472,386 probes
  Sex chrom homology mask: 1494 probes
  Pass 1: 4-feat blood GAM (16 workers)...
    20/46 blood samples, 25s, R²=0.4368
    40/46 blood samples, 38s, R²=0.4342
    46/46 blood samples, 40s, R²=0.4312
    Sex: 28 female, 18 male, 0 unknown
/usr/local/bin/build_norm_reference.py:247: RuntimeWarning: All-NaN slice encountered
  probe_coverage_median = np.nanmedian(blood_matrix, axis=1)
/usr/local/lib/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1593: RuntimeWarning: All-NaN slice encountered
  return fnb._ureduce(a,
    Probe coverage: 471,485/472,386 valid probes
  Preliminary 5-feat GAM on blood (16 workers)...
    20/46 blood prelim 5-feat, 37s, R²=0.9379
    40/46 blood prelim 5-feat, 57s, R²=0.9342
    46/46 blood prelim 5-feat, 57s, R²=0.9346
/usr/local/bin/build_norm_reference.py:335: RuntimeWarning: All-NaN slice encountered
  prelim_median = np.nanmedian(prelim_matrix, axis=1)
/usr/local/lib/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1593: RuntimeWarning: All-NaN slice encountered
  return fnb._ureduce(a,
    Probe mask: 16,591 masked (3.5%) — 10,786 low cov, 7,840 high var, 3,994 extreme
Wrote batch_reference.parquet (472,386 probes) to ./batch_reference.parquet
Wrote sex_calls.csv (46 samples) to ./sex_calls.csv
Wrote feature_stats.csv (46 samples) to ./feature_stats.csv
Build reference complete in 243.6s total