.coveragerc
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
MANIFEST.in
README.md
SECURITY.md
SUPPORT.md
mkdocs.yml
mypy.ini
pyproject.toml
ruff.toml
LICENSES/MIT.txt
docker/evaluator/Dockerfile
docker/evaluator/README.md
docs/DOCKER_REPLAY_VALIDATION.md
docs/ECOSYSTEM_GUIDE.md
docs/EXAMPLES.md
docs/INTERACTIVE_EXPLORER.md
docs/MODEL_EVAL_PLAN.md
docs/PACKAGE_PAPER_BLUEPRINT.md
docs/PUBLISHING_CHECKLIST.md
docs/PYTHON_PACKAGE.md
docs/REGENERATING_PUBLICATION_OUTPUTS.md
docs/RELEASE_NOTES_v1.0.0.md
docs/RELEASE_NOTES_v1.1.0.md
docs/RELEASE_NOTES_v1.1.1.md
docs/RELEASE_NOTES_v1.1.2.md
docs/RELEASE_NOTES_v1.2.0.md
docs/RELEASE_NOTES_v1.2.1.md
docs/REVIEWER_QUICKSTART.md
docs/SECURITY_AND_PRIVACY.md
docs/index.md
docs/user-manual/capabilities.md
docs/user-manual/cli-reference.md
docs/user-manual/core-concepts.md
docs/user-manual/data-dictionary.md
docs/user-manual/glossary.md
docs/user-manual/index.md
docs/user-manual/installation.md
docs/user-manual/live-model-testing.md
docs/user-manual/metrics-and-invariants.md
docs/user-manual/python-api.md
docs/user-manual/reporting-and-exports.md
docs/user-manual/reproducibility-contract.md
docs/user-manual/security-governance.md
docs/user-manual/troubleshooting.md
docs/user-manual/workflows.md
examples/README.md
examples/build_dashboard.py
examples/plan_live_run.py
examples/reproduce_frozen.py
requirements/evaluator-container.txt
requirements/package-runtime.txt
requirements/quality.txt
sbom/README.md
sbom/pqid-bench-evaluator-1.0.0.cdx.json
sbom/pqid-bench-python-1.1.0.cdx.json
sbom/pqid-bench-python-1.1.1.cdx.json
sbom/pqid-bench-python-1.1.2.cdx.json
sbom/pqid-bench-python-1.2.0.cdx.json
sbom/pqid-bench-python-1.2.1.cdx.json
src/pqid_bench/__init__.py
src/pqid_bench/__main__.py
src/pqid_bench/cli.py
src/pqid_bench/download.py
src/pqid_bench/live.py
src/pqid_bench/manifest.py
src/pqid_bench/metrics.py
src/pqid_bench/records.py
src/pqid_bench/replay.py
src/pqid_bench/reporting.py
src/pqid_bench/schemas.py
src/pqid_bench/version.py
src/pqid_bench/visualization.py
src/pqid_bench.egg-info/PKG-INFO
src/pqid_bench.egg-info/SOURCES.txt
src/pqid_bench.egg-info/dependency_links.txt
src/pqid_bench.egg-info/entry_points.txt
src/pqid_bench.egg-info/requires.txt
src/pqid_bench.egg-info/top_level.txt
src/pqid_bench/schemas/benchmark-record.schema.json
src/pqid_bench/schemas/evaluation.schema.json
src/pqid_bench/schemas/prompt.schema.json
src/pqid_bench/schemas/provider-attempt.schema.json
src/pqid_bench/schemas/response.schema.json
src/pqid_bench/schemas/run-manifest.schema.json
tests/README.md
tests/integration/test_release_reproduction.py
tests/release_parity/test_frozen_release.py
tests/unit/test_cli.py
tests/unit/test_core_bundle.py
tests/unit/test_documentation.py
tests/unit/test_download.py
tests/unit/test_live.py
tests/unit/test_manifest.py
tests/unit/test_metrics.py
tests/unit/test_publication_adapters.py
tests/unit/test_replay.py
tests/unit/test_reporting.py
tests/unit/test_repository_contract.py
tests/unit/test_schemas.py
tests/unit/test_visualization.py