# OCR Extraction Error Audit Sample Worksheet

> Source: https://netray.co/tools/ocr-extraction-error-audit-sample-worksheet
> Publisher: Netray (netray.co), AI and integration engineering for ERP and manufacturing systems.
> Section: Free Tools

## Short answer

Record a sample of reviewed documents by type and get field accuracy and clean-document rate per type and overall.

## Category

quality

## Industry

Manufacturing

## Audience

- Quality engineer
- AP manager
- Internal auditor

## Tool

**Kind:** worksheet

**Mode:** editable

**Columns:**

#### Document type

**Key:** doc_type

**Type:** select

**Options:**

- Supplier invoice
- Certificate of conformance
- Mill test report
- Packing list
- Purchase order
- Delivery note
- Other

#### Source or supplier

**Key:** source

**Type:** text

#### Documents sampled

**Key:** sample_docs

**Type:** number

#### Fields checked

**Key:** fields_checked

**Type:** number

#### Fields correct

**Key:** fields_correct

**Type:** number

#### Fields wrong or missing

**Key:** fields_wrong

**Type:** number

**Expr:** fields_checked - fields_correct

#### Docs with at least one error

**Key:** docs_with_error

**Type:** number

#### Field accuracy

**Key:** field_accuracy

**Type:** number

**Expr:** fields_correct / fields_checked * 100

**Format:** percent

#### Clean document rate

**Key:** clean_rate

**Type:** number

**Expr:** (sample_docs - docs_with_error) / sample_docs * 100

**Format:** percent

#### Most error-prone field

**Key:** worst_field

**Type:** text

**Rows:**

**Doc type:** Supplier invoice

**Source:** Supplier A (clean PDF)

**Sample docs:** 40

**Fields checked:** 600

**Fields correct:** 592

**Docs with error:** 6

**Worst field:** Tax amount

**Doc type:** Supplier invoice

**Source:** Supplier B (scanned)

**Sample docs:** 30

**Fields checked:** 450

**Fields correct:** 421

**Docs with error:** 14

**Worst field:** Invoice number

**Doc type:** Certificate of conformance

**Source:** Plating vendor

**Sample docs:** 25

**Fields checked:** 250

**Fields correct:** 233

**Docs with error:** 11

**Worst field:** Lot number

**Doc type:** Mill test report

**Source:** Steel service center

**Sample docs:** 20

**Fields checked:** 400

**Fields correct:** 358

**Docs with error:** 13

**Worst field:** Heat number

**Doc type:** Packing list

**Source:** Overseas supplier

**Sample docs:** 30

**Fields checked:** 240

**Fields correct:** 231

**Docs with error:** 7

**Worst field:** Quantity

**Totals:**

#### Total documents sampled

**Key:** sample_docs

**Agg:** sum

**Format:** integer

#### Total fields checked

**Key:** fields_checked

**Agg:** sum

**Format:** integer

#### Total fields correct

**Key:** fields_correct

**Agg:** sum

**Format:** integer

#### Total documents with an error

**Key:** docs_with_error

**Agg:** sum

**Format:** integer

**Summary:**

#### Overall field accuracy

**Key:** overall_accuracy

**Expr:** sum_fields_correct / sum_fields_checked * 100

**Format:** percent

**Primary:** true

#### Overall clean document rate

**Key:** overall_clean

**Expr:** (sum_sample_docs - sum_docs_with_error) / sum_sample_docs * 100

**Format:** percent

**Primary:** true

#### Fields wrong or missing

**Key:** wrong_fields

**Expr:** sum_fields_checked - sum_fields_correct

**Format:** integer

**Notes:** Compare the extracted value with the source document, not with another system. Sample documents at random within each type and include your poorest sources. Rows are examples: replace them with your audit data.

## Content

**Intro:** You cannot tune document capture without measuring it on your own paperwork. This worksheet records a sample audit by document type and computes field accuracy and the share of fully clean documents, ready to export to Excel.

**Sections:**

#### How to use the worksheet

**Body:** Pull a random sample of processed documents from each type and supplier group. For each row, count how many documents you sampled, how many fields you checked, how many were correct, and how many documents had at least one error. Name the most error-prone field so that follow-up targets the right problem. The sheet computes field accuracy and clean-document rate per row and in total.

**Bullets:**

- Check against the original image, not the ERP record.
- Sample at least a few dozen documents per type where you can.
- Add one row per supplier or source if they differ in quality.

#### What the numbers mean

**Body:** Field accuracy is correct fields over checked fields. Clean-document rate is documents without any error over documents sampled. The two differ because errors cluster: a bad scan produces several wrong fields in one document. Both numbers are useful. Field accuracy tells you how the model performs; clean-document rate tells you how much review or rework to expect.

#### Using the results

**Body:** Sort rows by clean-document rate to find the weak sources. A scanned certificate from one vendor often accounts for most errors, and a template, a request for digital documents or a tighter confidence threshold for that source can fix it. Repeat the audit after changes, and keep the sheet to show auditors that extraction quality is monitored.

#### Common mistakes

**Body:** Sampling only documents that were flagged for review hides errors that went through. Mixing document types in one row blurs the picture. And changing the list of fields between audits makes results incomparable, so fix the field list per document type first.

**Cta:** If you want sampling and scoring automated against your ERP and document store, Netray can build it on-prem with human approval on any write-back.

**Faq:**

#### How many documents should I sample?

**Answer:** Enough to see a stable result for each document type and the main sources, often a few dozen per group at minimum. Larger samples are needed to detect small changes or rare fields.

#### What counts as a wrong field?

**Answer:** Any checked field whose extracted value differs from the source in a way that matters, including missing values. Decide on rules for formatting differences, such as dates and currency symbols, before you start.

#### Why track the most error-prone field?

**Answer:** It shows where effort pays off. If one field such as lot number or tax amount causes most errors, targeted rules or training on that field are cheaper than retraining everything.

#### How often should I run the audit?

**Answer:** Monthly or quarterly is common, and after any change to the model, templates, suppliers or scan process. Regular sampling also gives you evidence for quality audits.

## Search terms

OCR accuracy audit template, OCR error audit worksheet, document extraction QA sample, invoice OCR accuracy audit excel, document AI quality sampling, extraction error log, OCR accuracy test sheet

---
Talk to an engineer: https://netray.co/contact?intent=erp_ai | Machine catalog: https://netray.co/agent/catalog.json