Base64-encoded serialized model artifact.
Wall-clock training time in seconds.
Per-feature importance/contribution.
Optionalfeature_Which kind of number feature_importance holds. Absent on sidecars that predate it.
Fitted preprocessing parameters (means/stds, vocabularies, bin edges, fill
values) learned during /train. Travels with the model and is replayed at
inference — never re-fit (plan §6.2).
Optionalholdout_Honest metrics on the locked holdout, scored exactly once (plan §8.2).
Train + validation metrics.
Number of training rows the model was fit on (excludes any locked holdout, forwarded or sidecar-carved).
Optionalvalidation_True when the sidecar computed metrics strictly out-of-sample (fit on train fold/split only, scored on held-out fold/split); set per run from the validation path taken. Absent on pre-C5 sidecars.
POST /trainresponse. Carries the serialized model plus the fitted preprocessing parameters (the anti-skew payload) and the deterministic metrics used to grade and rank the run.