Complete result settings for Retail dataset (table columns are sortable)
The experiments are described in Rooshenas and Lowd, Discriminative Structure Learning of Arithmetic Circuits, AIStats 16

Standard Deviation	L1 Penalty	Train CLL	Validation CLL	Test CLL	Node#	Edge#	Feature#	Learning Time
0.5	0.1	-1.597475	-1.559457	-1.693438	132657	306813	1448	4958.736157
0.1	0.1	-1.597475	-1.559456	-1.693438	132657	306813	1448	5335.873823
0.1	2	-1.598846	-1.558530	-1.691554	132657	306813	1448	8340.962980
0.1	0.5	-1.596105	-1.560178	-1.694416	132657	306813	1448	10369.504594
0.5	2	-1.599024	-1.558212	-1.690812	132657	306813	1448	12968.298518
0.5	0.5	-1.596128	-1.560224	-1.694513	132657	306813	1448	14365.447119
0.5	1	-1.596799	-1.558670	-1.693033	132657	306813	1448	14557.483925
0.1	1	-1.596516	-1.558565	-1.692441	132657	306813	1448	41800.678330