Notes

Accuracy of OCR and overProof is measured in comparison with the human corrections. We know human corrections in this sample are incomplete, and themselves contain errors, but they are the best we could find automatically from the NLA newspapers corpus, tagged as completely corrected then further filtered to those with at least 3 corrections, at least 40% of lines corrected and lowest third percentage of non-dictionary words.
Accuracy is measured by a separate process from that used to colour words in this output: the colouring process is heuristic, and not completely accurate.
Colour legend:
Text - OCR text corrected by human and/or overProof
Text - human and/or overProof corrections
Text - discrepencies between human and/or overProof
Text - human corrections not applied by overProof
Identified overProof corrections are calculated by the statistical calculation process, and shows those words changed by overProof which ALSO match human corrections. As human corrections are often wrong and incomplete, so too is this list.
Identified overProof non-corrections are calculated by the statistical calculation process, and shows those words in the overProof output which DO NOT MATCH human corrections. As human corrections are often wrong and incomplete, so too is this list. Words marked as [**VANDALISED] are those which have been changed by overProof but not by the human correction; as before, a missed human correction will be (incorrectly) classified as vandalisation by overProof.
Searchability of unique words refers to the distinct words in an article, and how many are present before and after correction. It is measure of how many of the words within an article could be used to find the article using a search engine.
Weighted Words refers to a calculation in which common words count for little (a fraction of a word) and unusual words count for more, in proportion to the log of the inverse of their frequency in the corpus. It may be an indicator of how well distinctive words in an article can be searched before and after correction.

Article ID 12843642, Article, Government Notice. Colonial Secretary's Office, Sydney, October 17, 1831., page 2 1831-10-24, The Sydney Herald (NSW : 1831 - 1842), 159 words, 5 corrections

Identified overProof corrections	PERSON INVITED FRIDAY UNDERTAKE ALEXANDER
Identified overProof non-corrections	LIGHTHOUSE TOR [**VANDALISED] MLEAY

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	142	88.0	97.2	76.5
Searchability of unique words	91	92.3	96.7	57.1
Weighted Words		93.1	96.7	52.7

NLA Trial Articles from 1831

Article ID 12843642, Article, Government Notice. Colonial Secretary's Office, Sydney, October 17, 1831., page 2 1831-10-24, The Sydney Herald (NSW : 1831 - 1842), 159 words, 5 corrections

Accumulated stats for 1 articles from year 1831

Raw OCR	Human Corrected	overProof Corrected
Government Notice.	Government Notice.	Government Notice.
Colonial Secretary's Office, Sydney,	Colonial Secretary's Office, Sydney,	Colonial Secretary's Office, Sydney,
October 17,1831.	October 17, 1831.	October 17, 1831.
IT being intended to erect a LIGHT- \|	IT being intended to erect a LIGHT-	IT being intended to erect a LIGHT- \|
at Newcastle, and to repair a	HOUSE at Newcastle, and to repair a	at Newcastle, and to repair a
liuilding in the neighbourhood tor the Residence ot	Building in the neighbourhood for the Residence of	building in the neighbourhood for the Residence of
the peison who may be placed in charge Persons	the person who may be placed in charge. Persons	the person who may be placed in charge Persons
disposed to undeitake tile VVoiK are "ívited to trans-	disposed to undertake the Work are invited to trans-	disposed to undertake the Work are "invited to transmit
mit Tenders to this Othce, at 12 o'Clock on Tnday the	mit Tenders to this Office, at 12 o'Clock on Friday the	Tenders to this Office, at 12 o'Clock on Friday the
18th ot November next, endorsed " Tender tor Light-	18th of November next, endorsed " Tender tor Light-	18th of November next, endorsed " Tender for Light-
house.'*	house."	houses
security will be required for the due performance	Security will be required for the due performance	security will be required for the due performance
of the Work to the satisfaction of a Board to be ap	of the Work to the satisfaction of a Board to be	of the Work to the satisfaction of a Board to be ap
appointed to survey the same ; and the Tender must	appointed to survey the same ; and the Tender must	appointed to survey the same and the Tender must
specify the names ot two persons willing to enter into	specify the names of two persons willing to enter into	specify the names of two persons willing to enter into
a Bond with the Contractor for the completion of the	a Bond with the Contractor for the completion of the	a Bond with the Contractor for the completion of the
Building within a reasonable time	Building within a reasonable time.	Building within a reasonable time
A plan and specification may be seen on application	A plan and specification may be seen on application	A plan and specification may be seen on application
ut the Office of Public Works, Sydney, where any fin.	at the Office of Public Works, Sydney, where any	at the Office of Public Works, Sydney, where any fin.
further information may also be obtained.	further information may also be obtained.	further information may also be obtained.
By Command of His Excellency the Governor.	By Command of His Excellency the Governor.	By Command of His Excellency the Governor.
ALEXASDER. M'EBATS	ALEXANDER. M'LEAY.	ALEXANDER. M'EBATS