Weight prediction (MoE daily curve)
Calls POST /api/weights/predict-daily-curve.
The daily MoE line is median/mean over anchor-level weights from combined pair Δkg (ridge / equal-weight / single expert).
It is not the same as applying the ridge meta-learner to each expert's daily curve.
Batch comparison
Select multiple pens (public batch_pk = Batch.batch_id). With fetch_new, each run loads training inputs for that pen only (batch_id is set per selection).
By default the list includes open pens (toggle “Closed only” to restrict). Each batch runs a separate predict-daily-curve with preferred_batch_pks: [one].
With Training window: last 7 days, each request intersects the form’s rolling week with that pen’s accommodation dates.
min(per_batch, floor(max_total / N)) after scaling if needed.
Chart controls
True vs MoE
Experts (daily)
Ridge MoE (pair-level)
pred_pair = Σᵢ coefᵢ · expert_i + intercept
Why daily MoE ≠ ridge on daily experts
Ridge combines pair Δkg predictions. The daily curve then takes median/mean over many anchor pairs. That two-step process does not equal applying ridge coefficients to per-expert daily medians.