Ethics
No human claims without human review.
Human-subjects status is unresolved. No human baseline has been collected. No synthetic respondents are used.
No-Fake-Data Rules
- No synthetic human respondents.
- No invented citations, model versions, prompt templates, or hidden exclusions.
- No claim of political bias unless the paper defines bias and validates the measure.
Claim Evidence
Ethics claims link to the page documenting the public validation packet and stay explicit about unresolved evidence.
| Claim | Evidence |
|---|---|
| Human-subjects status is unresolved and must be determined before human data collection. | IRB status , Collection readiness |
| No human baseline has been collected in the public validation packet. | Human status , Human annotation table |
| No external-anchor validation is represented as complete. | External status , External agreement table |
Evidence note
PoliBench is a public benchmark surface for model outputs under fixed political prompts. Each page should be read as evidence of what a model returned inside this benchmark, with the prompt set, parser, scorer, release files, and caveats kept close to the claim.
The site keeps the claims narrow on purpose. Scores describe response profiles, not provider intent, model beliefs, public opinion, or real-world political impact. Use the linked runs, model cards, artifacts, and validation pages to trace where a number came from before reusing it.
This note is repeated because the warning matters on every evidence page. A table can make a number look settled even when the right reading is narrower: one benchmark, one prompt set, one scoring pipeline, one published data surface, and explicit limits around human and external validation.