Blood manifest: 70 samples
Loaded 33,067,020 rows from 70 blood samples in 40.2s
GC reference: 472,386 probes
  Sex chrom homology mask: 1494 probes
  Pass 1: 4-feat blood GAM (16 workers)...
    20/70 blood samples, 24s, R²=0.5114
    40/70 blood samples, 39s, R²=0.5046
    60/70 blood samples, 53s, R²=0.5147
    70/70 blood samples, 59s, R²=0.5395
    Sex: 41 female, 29 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: 472,142/472,386 valid probes
  Preliminary 5-feat GAM on blood (16 workers)...
    20/70 blood prelim 5-feat, 52s, R²=0.9278
    40/70 blood prelim 5-feat, 85s, R²=0.9400
    60/70 blood prelim 5-feat, 117s, R²=0.9372
    70/70 blood prelim 5-feat, 124s, R²=0.9337
/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: 11,774 masked (2.5%) — 6,807 low cov, 5,885 high var, 2,569 extreme
Wrote batch_reference.parquet (472,386 probes) to ./batch_reference.parquet
Wrote sex_calls.csv (70 samples) to ./sex_calls.csv
Wrote feature_stats.csv (70 samples) to ./feature_stats.csv
Build reference complete in 437.0s total