madhvansh/Preflight IR evaluation run

Preflight TREC-style qrels/runs for malformed data, coverage differences, rank diagnostics, and task mismatches.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
qrelsPath to a TREC qrels file in the calling repository.yes
runPath to a TREC run file in the calling repository.yes
expected-taskIf set, require both '# task: ...' headers to match this value.no""
require-query-coverageFail instead of warn when qrels and run query sets differ.nofalse
require-judgedFail instead of warn when a run document is absent from qrels.nofalse
strict-ranksFail instead of warn on advisory rank-column anomalies.nofalse

no outputs