Blood manifest: 39 samples
Loaded 18,423,054 rows from 39 blood samples in 22.2s
GC reference: 472,386 probes
  Sex chrom homology mask: 1494 probes
  Pass 1: 4-feat blood GAM (16 workers)...
    20/39 blood samples, 24s, R²=0.4748
    39/39 blood samples, 35s, R²=0.5295
    Sex: 20 female, 19 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: 471,747/472,386 valid probes
  Preliminary 5-feat GAM on blood (16 workers)...
    20/39 blood prelim 5-feat, 37s, R²=0.9147
    39/39 blood prelim 5-feat, 55s, R²=0.9342
/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: 12,089 masked (2.6%) — 5,876 low cov, 7,192 high var, 3,385 extreme
Wrote batch_reference.parquet (472,386 probes) to ./batch_reference.parquet
Wrote sex_calls.csv (39 samples) to ./sex_calls.csv
Wrote feature_stats.csv (39 samples) to ./feature_stats.csv
Build reference complete in 209.4s total