ACRE Statistics Report

2023 General Election, Broomfield County, CO

Audit Engine version:'v2.32.X'

Run Date: 2026-08-15 04:12:54.839353 Copyright (c) Citizens' Oversight

Run Parameters & Characteristics

Review Tiers

Ballots are grouped into review-priority rounds (Ray, 2026-08-08): Round 1 alone already gives one representative ballot for every contest option/undervote/overvote/write-in-used check, on some contest-based style -- enough to catch a systemic (all-style) configuration error. Later rounds add coverage of the remaining contest-based style variants. A reviewer can stop after any round with that round's coverage guarantee already met, or split rounds across reviewers. No new ballots are drawn for this -- rounds are a relabeling of the same selected ballots used everywhere else in this report.

(8 raw coverage tiers -- including Tier 0/Preselected -- combined into 2 ACRE rounds (plus Round 0/Preselected) of ~300 ballots each -- see tier_round_target_size.)

Raw Tier Distribution

Rounds above are a presentation-layer bundling of these finer-grained raw tiers -- see compute_acre_tiers(). Contest-based styles this tier is the number of distinct contest-based styles this tier's own explicit picks touched -- the count that varies enormously by election (a small jurisdiction might have a dozen total contest-based styles; a large county can have several hundred), so use it, not raw ballot counts alone, when comparing this run's shape against a different election's. Dominant contest(s) is whichever contest had the most explicit picks within that tier (ties listed together); a contest with many style variants naturally dominates the tiers right before its coverage is exhausted, which is why the long tail tends to show one or two contests repeating across several consecutive tiers, not a bug or a sign of an unusually large sample. Votable options covered % / Strata coverage % are running totals through the END of that tier -- see the chart below for their full-resolution shape. Since preselected coverage is set for this run, Tier 0 (Preselected) appears as its own first row -- ballots an external hand-inspection process already covered, walked in their own given order (not coverage-optimized, so it can show flat spots before Tier 1 begins). Both percentage columns are the TRUE combined total from that row onward (preselected coverage plus everything ACRE's own tiers add on top), reaching 100% only at the very last tier.

Coverage vs. Ballots

Two set-cover progress curves against the same x-axis (cumulative ballots selected, at full per-pick resolution -- not just one point per tier): Votable options covered % is every contest option/undervote/overvote/write-in-used check, seen on SOME contest-based style -- it ramps up across Tier 1's own picks (rarest contest-based style/option sampled first) and then sits flat at 100%, which is why Round 1 alone is disproportionately valuable. Strata coverage % only reaches 100% once every contest-based style/layout-style variant of every votable option has also been verified -- the slower climb across the remaining tiers/rounds. Each point on the strata curve is labeled with its tier number, matching the Raw Tier Distribution table above. Both curves are general set-cover progress, not specific to any one contest or election, so this is the intended shape to compare across different elections' runs. Full per-pick data (not just tier-end snapshots) is in acre_coverage_curve.csv for anyone who wants to build their own visualization from it. When preselected coverage is set, both curves start with Tier 0 (Preselected) -- ballots an external process already covered, walked in their OWN given order rather than coverage-optimized, so expect flat spots there before Tier 1's rarest-first walk begins closing the remaining gap.

Contest Coverage

• Margin (votes) / Margin (%): the CVR's own reported margin of victory for that contest, not computed from the ACRE sample.
• RLA n: simplified risk-limiting-audit sample size (gamma=0, no-error case, risk limit 5%), computed across all ballot types together -- not from the ACRE sample. Uses the DILUTED margin (margin / total ballots with this contest on their style, including genuine blanks/undervotes) as an RLA's sampling universe requires, not the Margin (%) column above (which is undiluted -- margin / votes actually cast, excluding undervotes). Blank if the margin is zero/unknown, or if the contest is out of scope (include_uncontested_contests=False and this contest is uncontested).
• BMD ballots / Non-BMD ballots: selected ballots covering this contest, by type.
• BMD contest-based styles / Non-BMD contest-based styles: distinct contest-based styles, across the FULL CVR (not just the selected sample), that carry this contest -- the real denominator behind how many covering ballots to expect (contest-based styles x options is the strata minimum), since a contest can share a rare style family with several other rare contests.
• BMD primary picks / Non-BMD primary picks: of the covering ballots, how many were selected specifically because of THIS contest's own stratum, as opposed to being covered incidentally (cascade) by a pick made for some other contest on the same contest-based style. Ballots column can run well above contest-based styles x options while primary picks stays near it -- that's cascade coverage from sharing styles with other rare contests, not a bug.
• BMD write-ins / Non-BMD write-ins: of those, how many happen to carry a write-in in this contest -- not a coverage target (include_writeins default is FALSE), just an observed count.
• Round reaching RLA n: the earliest review round whose cumulative ballots covering this contest first reach the RLA n column's sample size. Blank if RLA n is unknown, or never reached even at full coverage (common for high-margin contests, where ACRE naturally needs very few ballots). This is a visibility/comparison metric only -- ACRE selects ballots for votable-option coverage, not by the simple random sampling an RLA's risk-limit math requires, so matching the ballot COUNT is not the same as having a valid RLA sample.
• No summed TOTAL row: a single ballot covers many contests at once (the cascade-coverage mechanism), so summing any column down would count most ballots many times over. True totals are in the parameters table above.