Run Date: 2026-09-10 19:10:54.354503 Copyright (c) Citizens' Oversight
This report provides a central location for all reports produced by AuditEngine.
The table below lists the attributes of this election. If the audit was run in cooperative workflow prior to any statement of the "Total Ballots Cast" then it will be missing below until that value is added to the job settings file.
| Election Name | 2022 November General, Somerset County, MD |
| District Population | 24620 |
| District Population Year | 2020 |
| Registered Voters | 14112 |
| Total ballots cast (official report) | 6958 |
| Voter Turnout of Registered Voters | 49.31% |
| Voter Turnout of Population | 28.26% |
| District Partisan Bias | Red (36% D vs 60% R) |
| Voting Equipment Vendor | ES&S |
| Job folder (required) | s3://us-east-1-audit-engine-jobs/US/MD/US_MD_Somerset_20221108_ocrmapped/ |
| Workflow methodology | public_oversight |
| Archives folder (required) | s3://us-east-1-audit-engine-election-data/US/MD/US_MD_Somerset_General_20221108/ |
| Number of LAT Images Archives spec'd | 1 |
| Number of LAT Results Files spec'd | 2 |
| EIF File Specified (required) | EIF_US_MD_Somerset_20221108_ocrmapped.csv |
| Number of style_masters archives spec'd | 1 |
| Number of Ballot Archives spec'd | 0 |
| Number of CVR files | 1 |
| Number of Verification Archives spec'd | 0 |
| Narrative Report | Narrative Report (Not Available) |
| Ballot Viewer App | BallotViewer (Not Available) |
| AdjudiTally App | AdjudiTally (Not Available) |
The following automatically generated reports are the most important reports for casual reviewers of the audit results.
| Stage / Report | Report Description |
|---|---|
| gen_final_report Final Consolidated Report |
This report provides a list of all reports available in the Audit. |
| gen_source_audit_report source_Totals_Report |
This report provides a review of each contest in detail based on the ballot images in the 'source' archives. If the CVR is available when this report is created, then the totals from the CVR will be included with the difference provided. |
| gen_cmpcvr_report Reconciliation Report |
This report provides details of disagreements between the voting system and the auditing result, as well as variants, such as write-ins, overvotes, and ballots which are 'gray-flagged' by AuditEngine for potential further review. This version of this report includes comparisons with the CVR, any manual results, and any adjudications. |
The reports listed here are in the same order as the pipeline stages that were executed to produce these audit results.
Many of these reports exist to allow for auditing analysts to check the progress of the audit.
All other supporting files and intermediate files can be found in the "Pipeline Report".
Most users may find what they need under "Main Reports", above.
| Stage / Report | Report Description |
|---|---|
| precheck precheck Report |
|
| gen_biabif Ballot Image Archive Metadata Report |
This report details information about the ballot image archives provided by the election district in terms of the metadata regarding each image file and its size, as well as the number of images in each file, repeated image files, etc. |
| preparse_cvr CVR Parsed Report |
This report describes the CVR files that have been parsed, showing the number of records in each file. |
| parse_eif Election Information File (EIF) Parse Report |
The Election Information File (EIF) contains the full description of the election in terms of what contests are included and what options are listed for each contest. The EIF file is usually generated from the CVR, if it is available (Public Oversight Workflow) or from other sources, such as the Logic and Accuracy Test results, in Cooperative Workflow. The EIF file can also be edited by hand, and commonly the number of write-ins need to be modified. |
| gen_fullbif gen_fullbif Delegation Report |
This is an internal report that provides the total number of delegations, their run time, and estimated cost for this stage. |
| imagematch Image_Match_Report |
This report is the result of a complete examination of all ballot images to create a cryptographic hash of each image file, to make it easy to local duplicated image files. There will be a hash value for each side of each sheet, but sometimes no "back" image is provided, so these may not be the same. When repeated images are detected, the first images detected are kept and all repeats of those are "skipped". If repeated images are detected, then it could have been caused by uploading results from the same machine multiple times. |
| gen_bif_report bif: Combined Metadata Report |
This report is similar to the "nocvr_bif: Combined Metadata Report" but now the CVR information has been combined and correlated. |
| writein_inspection_report Write-in inspection report |
This report shows write-in ballot images next to their OCR'd text, for manually reviewing whether the audit's write-in reading is accurate. |
| gen_template_tasklists Generate Templates Tasklist Report |
This report lists the style/page tasks queued for template generation, before the (often long-running) gentemplates stage actually runs them. |
| gentemplates gentemplates Delegation Report |
|
| gen_templates_report Templates Report |
This report shows the generated ballot style templates -- the target/oval positions AuditEngine will use to read votes -- for visual review before extraction. |
| detect_ml_targets ML Targets Detection Report |
This report shows the oval/target positions detected by the machine-learning detector, for visual review before they're used for option mapping. |
| gen_ml_detect_redlined_proofs Oval Detection Report |
This report shows detected oval positions overlaid on style page images, for visual review of the detector's accuracy. |
| map_option_names_ocr map_option_names_ocr Delegation Report |
|
| gen_ocr_mapping_report OCR Mapping Reports Index |
This report indexes the per-style OCR-based option-name mapping reports, for reviewing how ballot text was matched to EIF option names before TargetMapper promotion. |
| register_job_with_frontend Run TargetMapper App |
Link to launch the TargetMapper app for this job, for manually reviewing and promoting AI/OCR- proposed option-name mappings. |
| gen_option_proofs_report Option Proofs Report |
This report is to allow human-eye review of each option on all styles. We find that human-perception is particularly adept at finding any deviations among many that are the same. |
| gen_styles_report Style Redline Proofs Report |
This report is also called the "Redline Proofs report" and it provides an image of every style with the oval outlined with a rectangle and then marked with the name of the contest and options of that contest. We have found this report is relatively hard for human perception to review, and thus we have also the Option Proofs Report, which is much easier to check that each option is correctly mapped. However, it may be the case that an oval is left out, and it would not be shown at all on the option proofs report. Therefore, we still need this report, which should be reviewed only to verify that all ovals have been redlined. |
| bmd_map_report BMD map report |
This report shows how each BMD (Ballot Marking Device) summary page's printed contest and option text was matched to the EIF, for review before extraction relies on that mapping. |
| gen_acre_report ACRE Report |
This report launches the ACRE (All Contests Review & Evaluation) ballot-by-ballot review: a bounded sample of ballots, drawn to cover every contest option, undervote, overvote, and write-in-used check across every ballot style, grouped into review-priority rounds. Open the ACRE Review App from here to compare each selected ballot's image against its CVR record and record findings. |
| gen_acre_report ACRE Statistics Report |
This report documents the ACRE sample's run parameters, methodology, and coverage in detail: how many ballots were selected and why, the review-tier/round breakdown, oval and strata coverage progress, and per-contest margin, RLA sample size, and coverage statistics. Use this report to verify the sample itself was sound, not to review individual ballots. |
| gen_acre_report ACRE Review App (link for reviewers) |
Opens the standalone ACRE Review App with this run's ballot sample already loaded: compare each selected ballot's image against its CVR record, filter by round or contest, mark each contest as matching or not, and export the review. |
| extractvote extractvote Delegation Report |
This is an internal report that provides the total number of delegations, their run time, and estimated cost for this stage. |
| gen_source_audit_report source_Totals_Report |
This report provides a review of each contest in detail based on the ballot images in the 'source' archives. If the CVR is available when this report is created, then the totals from the CVR will be included with the difference provided. |
| parse_results_stdresults results Results Parsing Report |
|
| import_adjudications_cmpcvr import_adjudications_cmpcvr Report |
This report is available if adjudications have been imported after the comparison process. Once data has been imported, an adjudicated column will appear which corrects the Audit system results. |
| gen_cmpcvr_report Reconciliation Report |
This report provides details of disagreements between the voting system and the auditing result, as well as variants, such as write-ins, overvotes, and ballots which are 'gray-flagged' by AuditEngine for potential further review. This version of this report includes comparisons with the CVR, any manual results, and any adjudications. |
| gen_final_report Final Consolidated Report |
This report provides a list of all reports available in the Audit. |
| Pipeline Report Pipeline Report |
This report is updated as the processing pipeline is run, and provides the versions of all input files and outputs from each stage. |