Label hero claims as primary, supporting, or filler
Judges: One claim sentence from the hero or intro. Questions: choice:role - primary_claim, supporting_proof, filler_generality; score:weight - minor (1) to the one claim the page lives on (5). Action: Code runs the strike-and-reread loop by removing lowest-weight claims until one
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.3.36
Key facts
- Vertical
- Cross-industry
- Function
- Content & brand
- Status
- Idea
- Volume
- routine
- Value
- meaningful
- Risk
- low
- 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 “Label hero claims as primary, supporting, or filler”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.