Our main result is a generalization of Cappell's 5-dimensional splitting
theorem. As an application, we analyze, up to internal s-cobordism, the
smoothable splitting and fibering problems for certain 5-manifolds mapping to
the circle. For example, these maps may have homotopy fibers which are in the
class of finite connected sums of certain geometric 4-manifolds. Most of these
homotopy fibers have non-vanishing second mod 2 homology and have fundamental
groups of exponential growth, which are not known to be tractable by
Freedman--Quinn topological surgery. Indeed, our key technique is topological
cobordism, which may not be the trace of surgeries.Comment: 22 pages, exposition revised for better self-containmen