Release 0.6.0¶
Version 0.6.0 uses the independently trained chain
sr1_ou2024_v6_independent → zhead_ou2024_roman_med3_noisy_independent → sr2_ou2024_v5_romanonly_independent.
The dataset contains 23,845 spectra of 10,039 galaxies detected in H158, selected by true Hα or [O III] λ5007 flux above 10⁻¹⁶ erg s⁻¹ cm⁻². The galaxy-grouped split has 19,134 training spectra (8,042 galaxies), 2,327 validation spectra (992 galaxies), and 2,384 reserved test spectra (1,005 galaxies). Checkpoints were selected on validation only; all nine models were frozen before test predictions were generated. Evaluation uses 0.05 mag Roman photometric noise and the configured Rubin coadd noise. The previous 4,711-spectrum results used the checkpoint-selection partition and must be read as validation results.
Redshift — every reserved test spectrum, no S/N cut
Configuration |
NMAD |
Catastrophic outliers |
|---|---|---|
Grism + Roman F106/F129/F158 |
0.00133 |
0.67% (16/2,384) |
+ Rubin ugrizy, Year 1 |
0.00120 |
0.042% (1/2,384) |
+ Rubin ugrizy, Year 10 |
0.00123 |
0.042% (1/2,384) |
Nine-band photometry-only redshift control |
0.01152 |
None in 2,384 spectra |
Catastrophic means |Δz|/(1+z) > 0.15. The control removes the spectrum from the redshift head; its SR2 still reads the spectrum. No observed outliers in this finite sample does not imply a zero population outlier rate.
Line amplitude recovery — Roman three-band chain
Median recovered/true flux in detected line regions, binned by the best integrated line S/N in the grism. Lines below S/N 2 are excluded.
Recoverability |
n |
SR1 |
SR2 |
|---|---|---|---|
Marginal (2–3) |
764 |
0.58 |
0.90 |
Good (3–6) |
710 |
0.78 |
0.94 |
Strong (>6) |
345 |
0.81 |
0.89 |
SR2 configuration |
Marginal / good / strong recovery |
|---|---|
Roman three bands |
0.90 / 0.94 / 0.89 |
+ Rubin Year 1 |
0.90 / 1.01 / 0.98 |
+ Rubin Year 10 |
0.84 / 0.94 / 0.95 |
Photometry-only redshift control |
0.82 / 0.94 / 0.93 |
Frozen test caches, exact metrics, the split record and weight provenance are available with the dataset and models. Response and uncertainty audits from earlier weights do not validate this release. Line fluxes and ratios should not yet be treated as calibrated measurements; independent response and uncertainty calibration remain open.
The pending audits described above were completed in the 0.6.1 follow-up, using the same weights and test caches.