# Claim extraction filter for fact-checker

Judges: One sentence. Questions: noul:checkable\_claim - could this sentence be false; choice:claim\_type - credential, nap, statistic, study, url, procedure\_fact, superlative, none. Action: Only checkable claims enter the retrieval loop.

Grade: A — A clean typed decision \(yes/no, a pick from a list, or a level on a scale\) that is concrete, repeats routinely, and has meaningful value.. Score: 4.6.

Vertical: Agencies, media & creators.

Function: Research & education.

Status: Idea.

Volume: routine.

Value: meaningful.

Risk: moderate.

Evidence: null.

Flags: None.

- [Vertical](/verticals/agency_media_creator/)
- [Function](/functions/research_edu/)
- [Breaking-claim checkworthiness](/use-cases/breaking-claim-checkworthiness/)
- [Claim dedupe against fact-check archive](/use-cases/claim-dedupe-against-fact-check-archive/)
- [Press release vs. story churnalism score](/use-cases/press-release-vs-story-churnalism-score/)
- [Manuscript slush-pile triage](/use-cases/manuscript-slush-pile-triage/)
- [Newspaper article segmentation](/use-cases/newspaper-article-segmentation/)
- [Source-balance audit](/use-cases/source-balance-audit/)