ocr-verify

sample.pdf

Witness reading (Tesseract) vs VLM engine (simulated fabrication) · 5 pages checked · rendered at 200 DPI

PDF fixtures/sample.pdf AI output fixtures/engine_output

3
Pages flagged
of 5
101
Unsupported words
of 477 emitted
21.17%
Divergence
AI words the witness cannot place
Blank-page fabrication1Unsupported text1Dropped text1

How to read this

Tesseract read every page independently as a witness. It is not the ground truth — it is worse than the AI engine at almost everything. It has one property the AI engine lacks: it does not invent words. Each finding below is a place the two readings diverge, shown with the crop of the scan it came from.

Text merely moved on the page — reordered columns, floated captions, table cells read in a different sequence — is not reported: a word counts as unsupported only when it is absent from the witness reading of the whole page. Words below 40% witness confidence are excluded from the comparison entirely. Pages where the witness itself struggled are labelled, and their findings are hedged.

Flagged pages

Page 2

divergence 100.0% 70 AI words 0 witness words ink 0.00%
Blank-page fabrication 1.00 70 tokens
Scan region for this finding
Scan — full page

AI engine read

Chapter Two: Instrumentation and Method The barometric readings were corrected for temperature using the standard tables published by the Bureau in 1889. Each observer recorded the dry-bulb and wet-bulb temperatures at the moment of reading, and the corrections were applied during the reduction of the data at headquarters. Errors of the aneroid barometer were found to be systematic rather than random, and a correction curve was constructed for each instrument.

Witness read

(the witness read nothing here)

Page ink coverage is 0.00% and the witness read 0 words, yet the AI engine emitted 70.

Page 5

divergence 26.1% 119 AI words 88 witness words ink 1.65%
Unsupported text 1.00 31 tokens
Scan region for this finding
Scan — crop at 193,532

AI engine read

months were obtained at seven of them. The commission further resolved that a permanent magnetic observatory be established at Cape Ellery in the following season, with an annual grant of four hundred pounds charged to the hydrographic vote. The loss of the third party's notebooks is regretted.

Witness read

(the witness read nothing here)

Page 3

divergence 0.0% 72 AI words 109 witness words ink 2.24%
Dropped text 0.90 37 tokens
Scan region for this finding
Scan — crop at 192,485

AI engine read

(nothing)

Witness read

The self-registering apparatus failed twice during December, on both occasions owing to the freezing of the float chamber. Manual readings were substituted for the affected intervals and are marked accordingly in the published tables of the commission.

Every page

PageDivergenceAI wordsWitness words UnsupportedDroppedInkWitness In gate Findings
10.0%126126002.60%okyes0
2100.0%7007000.00%okyes1
30.0%721090372.24%okyes1
40.0%9090001.78%okyes0
526.1%119883101.65%okyes1