Blood manifest: 4 samples
Loaded 1,889,544 rows from 4 blood samples in 1.9s
GC reference: 472,386 probes
  Sex chrom homology mask: 1494 probes
  Pass 1: 4-feat blood GAM (16 workers)...
    4/4 blood samples, 1s, R²=nan
    Excluded 4 samples with chrX < 0.1 (data quality)
/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: 0/472,386 valid probes
  Preliminary 5-feat GAM on blood (16 workers)...
    4/4 blood prelim 5-feat, 1s, R²=nan
/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: 0 masked (0.0%) — 0 low cov, 0 high var, 0 extreme
Wrote batch_reference.parquet (472,386 probes) to ./batch_reference.parquet
Wrote sex_calls.csv (4 samples) to ./sex_calls.csv
Wrote feature_stats.csv (4 samples) to ./feature_stats.csv
Build reference complete in 16.2s total