METHODOLOGY

How Optics reads a headline cluster.

Optics is a headline-framing detector. It compares how outlets word the same event, then surfaces source spread, loaded words, content format, and confidence.

Last updated June 11, 2026.

1. Source ingestion

Optics scans 600+ RSS feeds from 490+ outlets every 5 minutes.

2. Event grouping

Articles are clustered by title overlap, entities, bigrams, description text, and sanity checks.

3. Wording gap

Multi-source stories get a 0-99 headline-contrast score plus loaded-word highlights.

4. Confidence

High requires 6+ sources and 3+ bias buckets. Medium requires 3+ sources and 2+ buckets. Two-source or heuristic matches stay developing.

5. Format checks

Optics flags news-vs-analysis, think-tank, opinion, podcast, live-update, review, and deal formats so high gaps are not overread.

6. Corrections

Bad matches, source-label disputes, and misleading Wording Gaps can be sent to corrections@optics.news for review.

The labels you'll see

Behind the labels, Optics keeps a 0-99 headline-contrast score for reliable matches. It is hidden for Needs Review stories so a thin match can't look more confident than it is.

Known limits

Examples of match quality

Source labels

Bias and factuality labels are outlet-level context. MBFC is the baseline label source while AllSides and Ad Fontes disagreements are tracked where available. Optics does not independently assign whole-outlet ideology scores.