uniform_probe_derivatives_kind
==============================

.. py:function:: t3toolbox.backend.uniform_fitting.uniform_probe_derivatives_kind(x0_data, order, weight = None, chunk_size = 100)

   .. code-block:: python

      def uniform_probe_derivatives_kind(
              x0_data:    typ.Tuple,
              order:      int,
              weight:     typ.Optional[typ.Sequence[float]] = None,
              chunk_size: typ.Optional[int] = 100,                 # W-chunk size for the 𝒥ᵀ assembly (docs/chunking.md)
      ) -> bfit.SamplingKind:                                  # sample = (ww, pp)


   The uniform **probe-derivatives** ``SamplingKind`` -- the twin of
   :py:func:`t3toolbox.backend.fitting.probe_derivatives_kind`.

   The forward / residual are the **packed** probe-derivative jets ``(d,)+(order+1,)+W+C+(N,)`` (order at
   axis 1, after the mode index ``d``), so the per-order weight ``ω`` is built with ``order_axis=1`` and
   ``sumsq`` / ``transpose`` are overridden to weight the correct axis (the inherited order-leading ``aw``
   would broadcast ``ω`` over ``d``).