These graphs show the aggregated classification over three different runs, where for every category (FN, TP, TN, FP) the minimal number over the different runs is taken. For example, if 500 traces are TP in the first run, 490 in the second, and 495 in the third, then the value 490 is used as aggregated value. As a result, these graphs can show discrepancies between the classifications in different runs.
For the Hybrid ILP Miner, there are discrepancies (note that some bars do not reach 1000). The biggest discrepancy occurs for a42f1n05. For every log where a discrepancy occurs, the Hybrid ILP Miner discovered different nets from this log over the three runs.