Consider a group of documents that has been selected from a much larger set of diverse documents so that the selected documents are as dissimilar from one another as possible. If we consider documents that are not highly related (connected, similar) to one another as being anomalous, then all of the documents that we have selected might be classified as anomalies. Is it possible for a data set to consist only of anomalous objects or is this an abuse of the terminology?

What will be an ideal response?

The connotation of anomalous is that of rarity and many of the definitions
of an anomaly incorporate this notion to some extent. However, there are
situations in which an anomaly typically does not occur very often, e.g., a
network failure, but has a very concrete definition. This makes it possible to
distinguish an anomaly in an absolute sense and for a situation to arise where
the majority of objects are anomalous. Also, in providing mathematical or
algorithmic definitions of an anomaly, it can happen that these definitions
produce situations in which many or all objects of a data set can be classified
as anomalies. Another viewpoint might say that if it is impossible to define
a meaningful normal situation, then all objects are anomalous. (“Unique” is
the term typically used in this context.) In summary, this can be regarded
as a philosophical or semantic question. A good argument (although likely
not an uncontested one) can be made that it is possible to have a collection
of objects that are mostly or all anomalies.