Blood manifest: 5 samples
Loaded 2,361,930 rows from 5 blood samples in 2.7s
GC reference: 472,386 probes
  Sex chrom homology mask: 1494 probes
  Pass 1: 4-feat blood GAM (16 workers)...
    5/5 blood samples, 10s, R²=0.3658
    Sex: 1 female, 4 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: 471,724/472,386 valid probes
  Preliminary 5-feat GAM on blood (16 workers)...
    5/5 blood prelim 5-feat, 17s, R²=0.9168
/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: 35,837 masked (7.6%) — 13,635 low cov, 22,976 high var, 10,112 extreme
Wrote batch_reference.parquet (472,386 probes) to norm_reference/batch_reference.parquet
Wrote sex_calls.csv (5 samples) to norm_reference/sex_calls.csv
Wrote feature_stats.csv (5 samples) to norm_reference/feature_stats.csv
Build reference complete in 76.5s total