LICENSE
README.md
pyproject.toml
src/sys1bench/__init__.py
src/sys1bench/cli.py
src/sys1bench/schemas.py
src/sys1bench.egg-info/PKG-INFO
src/sys1bench.egg-info/SOURCES.txt
src/sys1bench.egg-info/dependency_links.txt
src/sys1bench.egg-info/entry_points.txt
src/sys1bench.egg-info/requires.txt
src/sys1bench.egg-info/top_level.txt
src/sys1bench/adapters/__init__.py
src/sys1bench/adapters/base.py
src/sys1bench/adapters/embed_knn.py
src/sys1bench/adapters/encoder_finetuned.py
src/sys1bench/adapters/generic_http.py
src/sys1bench/adapters/hybrid_router.py
src/sys1bench/adapters/jev_openrouter.py
src/sys1bench/adapters/jev_typesafe.py
src/sys1bench/adapters/laya_local.py
src/sys1bench/adapters/llm_constrained.py
src/sys1bench/adapters/majority_prior.py
src/sys1bench/adapters/mock.py
src/sys1bench/adapters/nli_zeroshot.py
src/sys1bench/adapters/regex_keyword.py
src/sys1bench/analysis/__init__.py
src/sys1bench/analysis/arms.py
src/sys1bench/analysis/decision_value.py
src/sys1bench/analysis/decomposition.py
src/sys1bench/analysis/meta_eval.py
src/sys1bench/analysis/stats.py
src/sys1bench/data/__init__.py
src/sys1bench/data/canary/canary.jsonl
src/sys1bench/data/framings/guardrail_intent.yaml
src/sys1bench/data/framings/log_triage.yaml
src/sys1bench/data/framings/phishing_email.yaml
src/sys1bench/data/framings/policy_compliance.yaml
src/sys1bench/data/framings/support_tickets.yaml
src/sys1bench/framing/__init__.py
src/sys1bench/framing/expand.py
src/sys1bench/framing/perturb.py
src/sys1bench/generators/__init__.py
src/sys1bench/generators/base.py
src/sys1bench/generators/guardrail_intent.py
src/sys1bench/generators/log_triage.py
src/sys1bench/generators/multilingual_tickets.py
src/sys1bench/generators/phishing_email.py
src/sys1bench/generators/policy_compliance.py
src/sys1bench/generators/rag_relevance.py
src/sys1bench/generators/support_tickets.py
src/sys1bench/metrics/__init__.py
src/sys1bench/metrics/calibration.py
src/sys1bench/metrics/consistency.py
src/sys1bench/metrics/decision_value.py
src/sys1bench/metrics/efficiency.py
src/sys1bench/metrics/ordinal.py
src/sys1bench/metrics/robustness.py
src/sys1bench/metrics/selective.py
src/sys1bench/report/__init__.py
src/sys1bench/report/dashboard.py
src/sys1bench/report/latex.py
src/sys1bench/report/plots.py
src/sys1bench/report/results_doc.py
src/sys1bench/report/scorecard.py
src/sys1bench/runners/__init__.py
src/sys1bench/runners/benchmark_runner.py
src/sys1bench/runners/cache.py
src/sys1bench/runners/canary.py
src/sys1bench/runners/hybrid_sweep.py
src/sys1bench/runners/noul_consistency.py
src/sys1bench/runners/ordinal_probes.py
src/sys1bench/runners/robustness.py
src/sys1bench/runners/suite.py
src/sys1bench/runners/sweeps.py
tests/test_generators_framing.py
tests/test_metrics.py
tests/test_runner_end_to_end.py