← A mix of accurate and construed
What We Learned From Tracking the 2026 Campaign Ads
What it says
Since January, the Cook Political Report Battleground Issue Tracker, powered by AdImpact, has been tracking the top issues in the most competitive House and Senate races in the country, allowing us to see, in real time, the messages that candidates and their allies saw as the most effective at motivating voters. Here’s what we learned from tracking these ads, all on broadcast TV, from the primaries until November.
Why this verdict
Composite credibility prior: 0.58. The signals furthest from neutral were emotional loading (0.00), byline (0.00), ai text markers (0.04).
Stylometric markers scored 0.04 (0 = reads like edited human reporting, 1 = reads like generated filler). This is a weak prior and not a detection claim.
Signals
| Signal | Strength | Score |
|---|---|---|
|
Source trust
Reputation prior for the publishing domain. A starting point, not a verdict.
|
|
0.72 |
|
Corroboration
How many independent outlets carried a matching story, discounted when they are all low-tier.
|
|
0.32 |
|
Specificity
Density of named people, direct quotes, attributed statements, figures and dates.
|
|
0.74 |
|
AI text markers
Stylometric markers of generated filler. Higher means more machine-like. A weak prior, never proof.
|
|
0.04 |
|
Emotional loading
Clickbait, outrage and hedging language. Higher means more loaded.
|
|
0.00 |
|
Byline
Whether a named human author is credited.
|
|
0.00 |
Caveats
- The language model could not be reached for this article (AuthenticationError); it fell back to signal heuristics.
- Scored by signal heuristics only - no language model reviewed the claims in this article.
Provenance
| Assessed by | heuristics-only |
| Text available | Full article body |
| Found via | Search: 2026 House race campaign (discovery feed) |
| First seen | Nov 17, 22:00 EST |
| Composite signal prior | 0.58 |