System Transcription Sampled Errors

• Updated on Jan 7, 2026

• Published on Sep 24, 2025

• 1 minute(s) read

The System Transcription Sampled Errors table shows all sampled errors identified during Transcription QA in the selected time period. The System Transcription Sampled Errors table includes both field and table cell transcriptions. You can view 10, 25, 50, or 100 rows per page. To adjust the number of rows shown, use the drop-down at the bottom right of the table.

.png?sv=2026-02-06&spr=https&st=2026-07-27T09%3A18%3A43Z&se=2026-07-27T09%3A29%3A43Z&sr=c&sp=r&sig=OIfY%2Bs8dInuzjthaCAGeViIUAjC3fjm8oFH76VQVPgU%3D)

The table displays each error for the selected time period and data type (Name, Address, All Data Types, etc). By clicking on the arrow ( > ) at the left side of any row, the row will expand to show two columns for each error alongside the cropped field image as it appeared on the submitted page. If a field has multiple bounding boxes, all bounding boxes will be visualized. In the left column, you will find the Data Type, the Field Name, and the Layout in which the field information was sourced. In the right column, you will find the Entered Values and the consensus value (highlighted in green), along with the users associated with each value.

Filtering options

The following filtering options are available in the System Transcription Sampled Errors table:

• Date range: by default, these figures are generated with the last week's data, but can be recalculated for a custom date range.
• Error type: by default, all errors will be displayed, but you can specify whether only machine or manual entries to report instead.
• Entry type: by default, only fields will be displayed, but you can select table cells instead.
  • If you choose to display fields, an Auto-transcribed fields filter will appear for the table. By default, all fields are displayed, but you can specify if you want to show only auto-transcribed fields or exclude auto-transcribed fields from the table.
• Data type: errors can be filtered based on the data type of the field (e.g. Address versus Numeric).
• Layout variation type: by default, all layout variations will be displayed, but you can specify one or more layout variations to report instead.
• Layout entry: Select a layout variation to view accuracy data. After a layout variation is selected, you can further filter results by specific fields in Structured documents and by fields or table columns in Semi-structured documents. Field-level filtering is available only if field-specific accuracy targets are configured. To learn more, see Transcription Accuracy and Automation.