Found scandata at /var/tmp/autoclean/derive/breedinghorsesfo00wash/breedinghorsesfo00wash_scandata.xml.
Will skip page 1 because it's a cover page.
Will skip page 16 because it's a cover page.
Seeking title page...

Will skip the following pages as requested: 1,16
Title:      "breeding horses for the united states army"

Candidate pages:
  p. 2     329 total px    315.8 adj total

Word details for selected page:
  breeding     69 px
  horse;       67 px
  united       57 px
  states,      70 px
  army         66 px

Selected title page: 2
Identified leaf 2 as title page.
Marking leaf 2 as 'Title'.
Scandata has been modified. Saving log...