spectrum is a library that provides implementation of truth discovery algorithms, which estimate the correct object values as well as data source reliabilities. An object’s value can be discrete or continuous. For example, a person’s birthplace has a discrete domain, i.e, the birth location. Whereas a stock price is continuous.

In general, a truth discovery probablistic model has the following structure

The number of data sources and the number of values, $c_{s,o}$, could be of millions. This makes exact infernece on truth discovery models intractable. Therefore, we need to resolve to approximate inferences such as variational inference or MCMC sampling methods.