Skip to content

project

envelope_eval.py

Single-file Python scorer that labels model API responses into six outcome classes and reports gradeable yield alongside accuracy on the gradeable bodies.

Known aliases

  • envelope scorer
  • planted-envelope scorer

Relationships

No evidence-backed relationships are recorded.

Current clusters

build1 publisher

A six-label scorer keeps a 429 out of the model's error column

A dev.to post plants 24 fake API responses across six failure classes to show what a boolean pass rate does with a timeout, and its author says up front that the percentages are the fixture talking.

Publishers:dev.to

Reality

Evidence66
Adoption
Insufficient
Hype gap+10
Incentives65
Confidence70