How to read the corpus probabilities

When you see a case split into "46% mundane/natural, 25% indeterminable, 9% open non-human…", that is not a hunch dressed up as a number. It is a distribution: each incident case splits 100% among the same six mutually-exclusive and exhaustive narratives (a MECE model). Because every case uses the same partition, the numbers are comparable —one can coherently say which explanation accounts for more cases.

But comparable is not the same as true. These posteriors are structured analytical judgments, not empirically calibrated frequencies: the model says which explanation is most coherent with each case's analysis, not which is objectively correct. That is why the "indeterminable" narrative exists —the mass the available evidence does not let us assign—. It is the model's honesty valve: not everything can be resolved.

The corpus aggregate sums those posteriors into the expected number of cases per narrative. Being an expectation (linear), it holds even if the cases are correlated. When you doubt a number, don't look at the isolated decimal: look at the case's full posterior and how much mass lands in "indeterminable". That is where what we still don't know is on display.