Skip to navigation

nemo_gym.eval.comparison.suite.coverage

View as Markdown

Validate recorded and planned task coverage for suite comparisons.

Module Contents

Functions

NameDescription
_check_paired_coverage-
_task_indicesKeep task indices useful for locating missing inputs without overwhelming reports.
check_collection_coverageReturn collection inconsistencies separately from each source’s own evidence.
recorded_task_setsRead identities already recorded by aggregation; never derive repeat scores.
run_coverageDescribe a source’s own recorded and planned evidence independently of other runs.

API

nemo_gym.eval.comparison.suite.coverage._check_paired_coverage(
) -> None
nemo_gym.eval.comparison.suite.coverage._task_indices(
tasks: set[int]
) -> str

Keep task indices useful for locating missing inputs without overwhelming reports.

nemo_gym.eval.comparison.suite.coverage.check_collection_coverage(
) -> list[str]

Return collection inconsistencies separately from each source’s own evidence.

nemo_gym.eval.comparison.suite.coverage.recorded_task_sets(
) -> tuple[dict[int, frozenset[int]], list[str], bool]

Read identities already recorded by aggregation; never derive repeat scores.

Describe a source’s own recorded and planned evidence independently of other runs.