IRS13 Evaluation Parameters chapter E. M. Keen Harvard University Gerard Salton Use, reproduction, or publication, in whole or in part, is permitted for any purpose of the United States Government. 11-66 Normalized Recall Req. Option I Option II Option III A .8125 .8000 .8135 B .8250 .800o .8135 C .8010 .8000 .7810 D .Sooo .8100 .7850 E .SOOo .8080 .7900 F .8000 .8060 .7950 G .8000 .80[OCRerr]o .7990 H .800o .80[OCRerr] .8080 I .80oo .8010 .8150 a) Results of Nine I[OCRerr]rpothetical Requests 4) ~ [OCRerr] .20 .15 4) [OCRerr] .I0[OCRerr] 4) N [OCRerr] .05 E C z A Option I 0 Option Ir I I 3 Individual Requests 4) 4) [OCRerr] [OCRerr] .20- [OCRerr]. 151 [OCRerr] .10- 4) N E U- T z 6 A Option I 0 Option lir N ¼ ½ ~n~A 131 Individual I I 6 Requests 6 Requests better on Option m (66.7%) 3 Requests better on Option I (33.3%) b) Plot of Differences Comparing Options I and IL. 6 Requests better on Option I (66.7%) 3 Requests better on Option III (33.3%) c) Plot of Differences Comparing Options I and III. Illustration of Method Used to Compile Magnitude Difference Plot Fig. 36