Skip to content

Judge checker problems instead of excluding them #2

Description

@natedemoss

load_problems skips anything whose problem_type is not diff, because
exact-match scoring cannot grade a problem with many valid outputs. In a sample
of 25 problems, 5 were checker — so this is roughly 20% of the corpus excluded
from eval, and the excluded slice is not random.

Codeforces ships a checker program per problem. open-r1/codeforces-cots has a
checker_interactor config that appears to carry them.

What this needs:

  • Load the checker source alongside the problem
  • Run it as checker(input, expected_output, actual_output) -> accept/reject
    in the same sandbox the solutions run in
  • A Verdict path for "checker itself crashed", which is a harness failure and
    must not be silently counted as a wrong answer

Until this lands, every published pass@1 is measured on the exact-match subset
only, and the README should keep saying so.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    evalEvaluation harness and metricsjudgeAffects how solutions are scored -- distorts every published number

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions