Found scandata at /var/tmp/autoclean/derive/smithsonianmisce721922smit/smithsonianmisce721922smit_scandata.xml.
Will skip page 1 because it's a cover page.
Will skip page 754 because it's a cover page.
Seeking title page...

Will skip the following pages as requested: 1,754
Title:      "smithsonian miscellaneous collections"

Candidate pages:
  p. 5     351 total px    315.9 adj total

Word details for selected page:
  smithsonian.    134 px
  miscellaneous   109 px
  collections     108 px

Selected title page: 5
Identified leaf 5 as title page.
Marking leaf 5 as 'Title'.
Scandata has been modified. Saving log...