Blood manifest: 15 samples
Loaded 7,085,790 rows from 15 blood samples in 8.7s
GC reference: 472,386 probes
  Sex chrom homology mask: 1494 probes
  Pass 1: 4-feat blood GAM (16 workers)...
    15/15 blood samples, 16s, R²=0.7336
    Sex: 6 female, 9 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: 471,757/472,386 valid probes
  Preliminary 5-feat GAM on blood (16 workers)...
    15/15 blood prelim 5-feat, 22s, R²=0.9621
/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: 21,149 masked (4.5%) — 9,791 low cov, 12,248 high var, 3,011 extreme
Wrote batch_reference.parquet (472,386 probes) to ./batch_reference.parquet
Wrote sex_calls.csv (15 samples) to ./sex_calls.csv
Wrote feature_stats.csv (15 samples) to ./feature_stats.csv
Build reference complete in 101.3s total