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 36865543, Article, THE BRIDAL HOUR., page 4 1829-03-27, The Australian (Sydney, NSW : 1824 - 1848), 253 words, 5 corrections

Identified overProof corrections	POOL DRIES TOWN SUMMER EFFECTED HE
Identified overProof non-corrections	SEAR [VANDALISED] DOME [VANDALISED]

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	221	95.0	98.6	72.7
Searchability of unique words	164	96.3	98.8	66.7
Weighted Words		96.8	98.9	66.7

NLA Trial Articles from 1829

Article ID 36865543, Article, THE BRIDAL HOUR., page 4 1829-03-27, The Australian (Sydney, NSW : 1824 - 1848), 253 words, 5 corrections

Accumulated stats for 1 articles from year 1829

Raw OCR	Human Corrected	overProof Corrected
THE BRIDAL HOfTR	THE BRIDAL HOUR.	THE BRIDAL HOfTR
The gliding fish that takes his play	The gliding fish that takes his play	The gliding fish that takes his play
In shady nook of streamlet cool,.	In shady nook of streamlet cool,	In shady nook of streamlet cool,.
Thinks not how waters pass away.	Thinks not how waters pass away,	Thinks not how waters pass away.
And stimmpr drip* *h» nnnl.	And summer dries the pool.	And summer dries the pool.
The bird beneath his leafy dome	The bird beneath his leafy dome	The bird beneath his leafy some
. Wlio trills his carol, loud and clear* ~	Who trills his carol, loud and clear,	Who trills his carol, loud and clear ~
, Thinks not how soon his verdant home	Thinks not how soon his verdant home	, Thinks not how soon his verdant home
The lightning's breath may sear.	The lightning's breath may sear.	The lightning's breath may year.
Shall I within my bridegroom's bower	Shall I within my bridegroom's bower	Shall I within my bridegroom's bower
With braids of budding roses twined.	With braids of budding roses twined.	With braids of budding roses twined.
Look forward to a coming hour	Look forward to a coming hour	Look forward to a coming hour
* When be may prove unkind }	When he may prove unkind ?	When he may prove unkind }
The bee reigns in hit waxen cell,	The bee reigns in his waxen cell,	The bee reigns in his waxen cell,
. The chieftain in his stately hold,	The chieftain in his stately hold,	The chieftain in his stately hold,
' \ To-morrow's earthquake — who can tell ? '	To-morrow's earthquake—who can tell ?	' \ To-morrow's earthquake — who can tell ? '
May both in ruin fold. - '	May both in ruin fold.	May both in ruin fold. - '
Permanent writing; the London Weekly Review	Permanent writing; the London Weekly Review	Permanent writing; the London Weekly Review
remarks, may be easily efiected by rubbing fine	remarks, may be easily effected by rubbing fine	remarks, may be easily effected by rubbing fine
pounce, or what is preferable phosphate of lime	pounce, or what is preferable phosphate of lime	pounce, or what is preferable phosphate of lime
from burnt bones, over the paper previously, and	from burnt bones, over the paper previously, and	from burnt bones, over the paper previously, and
making use of the composition metallic pencils,	making use of the composition metallic pencils,	making use of the composition metallic pencils,
which consist of three parts lead, two of bismuth,	which consist of three parts lead, two of bismuth,	which consist of three parts lead, two of bismuth,
and one of tin, melted together. This is a desira	and one of tin, melted together. This is a desirable	and one of tin, melted together. This is a desirable
ble mode of writing for surveyors, or others em	mode of writing for surveyors, or others	mode of writing for surveyors, or others employed
ployed out of doors, where pen and ink cannot be	employed out of doors, where pen and ink cannot	out of doors, where pen and ink cannot be
obtained, it being almost as indelible as common	be obtained, it being almost as indelible as	obtained, it being almost as indelible as common
ink. ''? '. '. ? ''..?? - _ ' .'	common ink.	ink. ''? '. '. ? ''..?? - _ ' .'
The. new railway between Manchester and Liver	The new railway between Manchester and Liver-	The. new railway between Manchester and Liverpool
pool passes under the'town of Liverpool in a tun	pool passes under the town of Liverpool in a tunnel	passes under the town of Liverpool in a tunnel
nel cut through the. solid rock, 16 feet high, S2	cut through the solid rock, 16 feet high, 22	cut through the. solid rock, 16 feet high, 22
wide, and a mile and a quarter in length. It	wide, and a mile and a quarter in length. It	wide, and a mile and a quarter in length. It
emerges into day light on the top ,of Edge-hill,	emerges into day light on the top of Edge-hill,	emerges into day light on the top of Edge hill,
looking down upon Liverpool.	looking down upon Liverpool.	looking down upon Liverpool.