Table 2.

Results of re-ranking combined proposals of GLN and RetroSim on USPTO-50K test data

Models	Top-N accuracy (%)						Mean Reciprocal Rank
	1	3	5	10	20	50
RetroSim	35.7 ($\pm 0$)	53.3 ($\pm 0$)	62.0 ($\pm 0$)	73.4 ($\pm 0$)	82.3 ($\pm 0$)	88.5 ($\pm 0$)	0.477 ($\pm 0.000$)
RetroSim + Graph-EBM	51.8 ($\pm 0.43$)	74.5 ($\pm 0.37$)	81.1 ($\pm 0.17$)	86.4 ($\pm 0.13$)	88.5 ($\pm 0.02$)	88.9 ($\pm 0.00$)	0.644 ($\pm 0.004$)
GLN	51.7 ($\pm 0.33$)	67.8 ($\pm 0.43$)	75.1 ($\pm 0.32$)	83.2 ($\pm 0.12$)	88.9 ($\pm 0.11$)	92.4 ($\pm 0.06$)	0.620 ($\pm 0.003$)
GLN + Graph-EBM	52.3 ($\pm 0.01$)	74.9 ($\pm 0.27$)	82.0 ($\pm 0.18$)	88.0 ($\pm 0.02$)	91.4 ($\pm 0.11$)	93.0 ($\pm 0.08$)	0.652 ($\pm 0.001$)
GLN + RetroSim + Graph-EBM	52.5 ($\pm 0.10$)	75.7 ($\pm 0.15$)	83.1 ($\pm 0.34$)	89.7 ($\pm 0.18$)	93.1 ($\pm 0.12$)	94.8 ($\pm 0.06$)	0.658 ($\pm 0.000$)

Bolded values represent best top-N accuracies and best MRR across both GLN and RetroSim (including their individually re-ranked versions)