Methodology

What we publish

For each 2026 race we cover (U.S. Senate and Governor today, the House later), we publish a fixed set of short statements and, for each researched candidate, whether the public record shows them agreeing, disagreeing, or taking no clear position. Every agree or disagree comes with a verbatim quote, a link, a date and the type of source.

All of it is public on this site: every finding, every public challenge and agreement, and every ruling.

Who we research

Every candidate who qualified for the ballot is listed. We research a candidate if they are a Democratic or Republican nominee, an incumbent, raised at least $50,000 according to the Federal Election Commission, or reached 5 percent in a public poll. Everyone else appears as "Not researched: below our published threshold". The rule is the same in every state.

A researched candidate is marked Limited data when we could find fewer than 6 sourced positions for them.

Candidate lists come from state election offices first. Federal Election Commission records and Wikidata are used only to cross-check. A race's list is marked final only after a person checks it against the certified state list.

The statements

Senate candidates are asked about a federal set of statements; Governor candidates about a set written for their state. Some races add up to four statements on issues specific to that race.

Every statement follows the same rules: one issue, declarative, answerable with agree or disagree, under 140 characters, with no loaded words, no party or ideology words, no candidate names and no slogans. It must be concrete enough that a public record can confirm or deny it. Across a set, "agree" lines up with either side at most 60 percent of the time.

Every statement passes an automated neutrality and balance check (no single side may line up with "agree" on most of a deck) and is accepted by the VoteVera editor. Anyone can challenge the wording of a statement.

How a position is found

An AI research assistant (Claude, made by Anthropic) searches each candidate's public record, one candidate at a time, using web search and page fetching only. For each statement it must return a stance, a confidence, and sources with the exact words. Sources are ranked, strongest first:

Mechanical rules apply to every answer: no source, no position. An agree or disagree without a link, a verbatim quote of at most 300 characters and a date becomes "no clear position". Ballotpedia and Vote Smart are never cited because of their license terms. Positions only inferred from related views are never counted unless a person approves them. When sources conflict over time, the newest vote or self-stated position wins.

How it is checked

A second, independent pass checks every cited source. A program fetches each page and looks for the quote (it must match at least 85 percent of the words). A separate AI checker, with a different prompt and without being told the first stance, re-reads the page and reports whether the quote is there, whether the words are the candidate's own, and what stance it would record. Each page is also saved to the Internet Archive, so a deleted campaign page does not break the evidence.

A source counts as verified when either check finds the quote and the checker does not say the words belong to someone else. A position with no verified source is downgraded to "no clear position".

Review in three public phases

1. Phase 1: AI findings, public. Research and verification results are published with every source, so anyone can inspect them. Findings that pass verification are accepted by the VoteVera editor.
2. Phase 2: public check. Anyone who signs in with an email address can agree with a specific finding or challenge it. A challenge must include a link and the exact quote that shows the finding is wrong or out of date. It counts in full when the link is from the candidate's own verified accounts or an official government site (see Challenges and evidence); other posts appear under Unverified evidence. Posts are public immediately; anyone can report one, and a post reported by several people is hidden until it is looked at.
3. Phase 3: rulings. An AI tiebreaker (Claude) weighs each challenge's evidence by the same source ranking and drafts a ruling with its reasons. The editor publishes it. Approved rulings are shown on the finding with the date and the reason.

Findings the verification pass could not confirm (the quote was not found, the checker disagreed, sources conflicted, or the position was only inferred) are held back and shown as no clear position until a challenge or the AI tiebreaker settles them. Each finding shows how it was checked.

Challenges and evidence

A challenge must bring evidence: a link and the exact words on that page. So that fake accounts and copy-paste campaigns cannot outweigh real evidence, we check where the link points.

Accepted sources. A challenge counts in full when its link comes from:

• the challenged candidate's own verified accounts and sites: campaign site, official site, and verified accounts on X, Facebook, Instagram, YouTube, TikTok, Threads or Bluesky. Each finding lists them under "Accepted sources". A social media link must point to that exact account, for example a post on the candidate's own profile. A lookalike account, or a link that does not show whose post it is, does not count;
• an official government site: congress.gov, senate.gov, house.gov, govinfo.gov, fec.gov, plus the race state's own governor, legislature and election sites (listed on each finding's page);
• a recorded debate the candidate took part in, from the organizer's own page, when it is listed among the candidate's sources;
• an archived snapshot of any of these (web.archive.org).

Any other link, news articles included, is still posted, but under Unverified evidence: public, collapsed, and not counted as a challenge until an editor approves it. Link shorteners are refused because they hide where a link goes, and tracking parameters are removed from every link.

New accounts and repeats. Posts from accounts less than 24 hours old also go under Unverified evidence. When another account posts the same link on the same finding, the later post is collapsed and both are flagged for an editor.

Limits. Signing in and posting pass a quick check that you are a person (Cloudflare Turnstile). Temporary and disposable email addresses cannot sign in. Accounts less than a day old can post 3 times a day and everyone else 20, with further limits per network. A post reported by 3 different people is hidden until it is reviewed.

Confidence

Confidence is capped by the strongest source: votes and the candidate's own channels can reach high; questionnaires and interviews medium at most; posts and press quotes lower. It is shown as High (0.8 or more), Medium, or Low (below 0.6).

Order and presentation

Candidates are listed alphabetically by last name in every race. Agree and disagree are always shown with a word and a symbol, never by color alone. Candidates and parties never get a color. Party labels are shown as words, as they appear on the ballot.

Data and code

The site reads the same versioned data files the VoteVera app uses. Each release has a date-stamped version and every race file a content hash, so any finding can be traced to the exact file it came from. Challenges and agreements posted here are exported as JSON for the phase 3 review.

Limits

Public records are incomplete, candidates change their minds, and AI makes mistakes. "No clear position" means we did not find one, not that the candidate has none. That is why every finding is open to challenge, and why a person approves every change.