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.
AA 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.4.60
Key facts
- Vertical
- Agencies, media & creators
- Function
- Research & education
- Status
- Idea
- Volume
- routine
- Value
- meaningful
- Risk
- moderate
- Evidence
- —
- Flags
- None
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “Claim extraction filter for fact-checker”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.