The coherentist theory of justification provides a response to the sceptica
l challenge: even though the independent processes by which we gather infor
mation about the world may be of dubious quality, the internal coherence of
the information provides the justification for our empirical beliefs. This
central canon of the coherence theory of justification is tested within th
e framework of Bayesian networks, which is a theory of probabilistic reason
ing in artificial intelligence. We interpret the independence of the inform
ation gathering processes (IGPs) in terms of conditional independences, con
struct a minimal sufficient condition for a coherence ranking of informatio
n sets and assess whether the confidence boost that results from receiving
information through independent IGPs is indeed a positive function of the c
oherence of the information set. There are multiple interpretations of what
constitute IGPs of dubious quality. Do we know our IGPs to be no better th
an randomization processes? Or, do we know them to be better than randomiza
tion processes but not quite fully reliable, and if so, what is the nature
of this lack of full reliability? Or, do we not know whether they are fully
reliable or not? Within the latter interpretation, does learning something
about the quality of some IGPs teach us anything about the quality of the
other IGPs? The Bayesian-network models demonstrate that the success of the
coherentist canon is contingent on what interpretation one endorses of the
claim that our IGPs are of dubious quality.