The data is freely available here along with the codebook etc.
For each conflict coded in the dataset, the list of scholarly references is now available here.
Miguel et al. (2004) popularize the use of this dataset for measuring civil wars among economists. See this paper for why this dataset may be better than the COW data.
Most recently used by Besley and Persson (2011).
A spin-off data is the Conflict Site Dataset, which provides the centroid and the radius of the zone of each conflict recorded in the Armed Conflict Database. A grid-cell (0.5 x 0.5 arc-degree) version is available as part of the PRIO-GRID data. Used by Campante, Do, and Guimares (2014), to show that conflicts are more likely to occur in the areas closer to the capital city. While the data quality should be worse than ACLED, it is useful if research concerns those countries not covered by ACLED.