.gitattributes
.gitignore
.pre-commit-config.yaml
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MAINTAINING.md
README.md
SECURITY.md
THIRD_PARTY_NOTICES.md
pyproject.toml
.context/todos.md
.github/PULL_REQUEST_TEMPLATE.md
.github/dependabot.yml
.github/ISSUE_TEMPLATE/bug_report.yml
.github/ISSUE_TEMPLATE/config.yml
.github/ISSUE_TEMPLATE/feature_request.yml
.github/scripts/check_generator_rows.py
.github/workflows/dependency-review.yml
.github/workflows/generators-live-test.yml
.github/workflows/package-build.yml
.github/workflows/pr-title.yml
.github/workflows/release-pypi.yml
.github/workflows/security-audit.yml
.github/workflows/tests-noop.yml
.github/workflows/tests.yml
configs/train-parent.yaml
configs/train-v7.yaml
configs/train.yaml
configs/experiments/v11a.yaml
configs/experiments/v11b.yaml
configs/experiments/v12.yaml
configs/experiments/v13.yaml
configs/experiments/v14.yaml
configs/experiments/v15.yaml
configs/experiments/v16.yaml
configs/experiments/v17.yaml
configs/experiments/v18.yaml
configs/experiments/v19-seed1.yaml
configs/experiments/v19.yaml
configs/experiments/v20.yaml
data/README.md
data/SHA256SUMS
data/sources.md
data/checks/verify_synth_labels.py
data/checks/verify_synth_pairs.py
data/generators/README.md
data/generators/gen_adequacy_openrouter.py
data/generators/gen_documents.py
data/generators/gen_documents_openrouter.py
data/generators/gen_flips_openrouter.py
data/generators/gen_paraphrases_openrouter.py
data/generators/llm_client.py
data/generators/gen_adequacy/batches.jsonl
data/generators/gen_adequacy/gen_eval.jsonl
data/generators/gen_adequacy/gen_train.jsonl
data/generators/gen_adequacy/stats.json
data/generators/gen_adequacy/verify.jsonl
data/generators/gen_flips/batches.jsonl
data/generators/gen_flips/gen_eval.jsonl
data/generators/gen_flips/gen_train.jsonl
data/generators/gen_flips/stats.json
data/generators/gen_flips/verify.jsonl
data/generators/gen_mixed_pilot/docs.jsonl
data/generators/gen_mixed_pilot/gen_eval.jsonl
data/generators/gen_mixed_pilot/gen_train.jsonl
data/generators/gen_mixed_pilot/stats.json
data/generators/gen_mixed_pilot/verify.jsonl
data/generators/gen_paraphrases/candidates.jsonl
data/generators/gen_paraphrases/paraphrases.jsonl
data/generators/gen_pilot_qwen/docs.jsonl
data/generators/gen_pilot_qwen/gen_eval.jsonl
data/generators/gen_pilot_qwen/gen_train.jsonl
data/generators/gen_pilot_qwen/stats.json
data/generators/gen_pilot_qwen/verify.jsonl
data/generators/gen_v16/docs.jsonl
data/generators/gen_v16/gen_eval.jsonl
data/generators/gen_v16/gen_train.jsonl
data/generators/gen_v16/stats.json
data/generators/gen_v16/verify.jsonl
data/generators/gen_weak/docs.jsonl
data/generators/gen_weak/gen_eval.jsonl
data/generators/gen_weak/gen_train.jsonl
data/generators/gen_weak/stats.json
data/generators/gen_weak/verify.jsonl
data/synthetic/adequacy_gen.jsonl
data/synthetic/adequacy_gen_eval.jsonl
data/synthetic/flips_v20.jsonl
data/synthetic/flips_v20_eval.jsonl
data/synthetic/generated_v16.jsonl
data/synthetic/generated_v16_eval.jsonl
data/synthetic/generated_v18.jsonl
data/synthetic/generated_v18_eval.jsonl
data/synthetic/replay_v14_multistep.jsonl
data/synthetic/teacher_multistep_v14.jsonl
data/synthetic/teacher_v5_qwen35-4b.jsonl
docs/architecture.md
docs/inference.md
evaluation/README.md
evaluation/bench_local.py
evaluation/calibrate_mix.py
evaluation/jevbench.md
evaluation/multistep_eval.py
evaluation/pair_accuracy.py
evaluation/pair_eval.py
evaluation/question_sensitivity.py
evaluation/results.md
evaluation/jevbench/jevbench.sh
evaluation/jevbench/jevbench_cold_warm.py
evaluation/jevbench/paired.py
examples/strands/README.md
examples/strands/_client.py
examples/strands/tool_call_intervention.py
research/README.md
research/generations.md
research/history.md
research/data/heldout_short.csv
research/data/indist.csv
research/data/jevbench_families.csv
research/data/jevbench_latency.csv
research/data/jevbench_results.csv
research/data/jevbench_tasks.csv
research/data/latency_questions.csv
research/data/multistep_and_generated.csv
research/data/probe_heldout_choice.csv
research/data/runs.csv
research/data/training_history.csv
research/figures/architecture.svg
research/figures/fit_vs_generalisation.svg
research/figures/fit_vs_generalisation_by_kind.svg
research/figures/hard_families.svg
research/figures/heldout_short.svg
research/figures/heldout_trajectory.svg
research/figures/jevbench_accuracy.svg
research/figures/jevbench_brier.svg
research/figures/jevbench_ece.svg
research/figures/jevbench_secondary.svg
research/figures/jevbench_tiers.svg
research/figures/latency_vs_questions.svg
research/figures/latency_vs_tokens_v18.svg
research/figures/multistep.svg
research/figures/question_sensitivity.svg
research/figures/training_v17_loss.svg
research/figures/training_v17_val_acc.svg
research/figures/training_v17_val_loss.svg
research/figures/trajectory.svg
research/figures/trajectory_brier.svg
research/figures/trajectory_ece.svg
research/preregistrations/PREREGISTRATION-v10.md
research/preregistrations/PREREGISTRATION-v11.md
research/preregistrations/PREREGISTRATION-v12.md
research/preregistrations/PREREGISTRATION-v13.md
research/preregistrations/PREREGISTRATION-v14.md
research/preregistrations/PREREGISTRATION-v15.md
research/preregistrations/PREREGISTRATION-v16.md
research/preregistrations/PREREGISTRATION-v17.md
research/preregistrations/PREREGISTRATION-v18.md
research/preregistrations/PREREGISTRATION-v19-calmix.md
research/preregistrations/PREREGISTRATION-v19-seed1.md
research/preregistrations/PREREGISTRATION-v19.md
research/preregistrations/PREREGISTRATION-v20.md
research/preregistrations/PREREGISTRATION-v9.md
research/preregistrations/README.md
research/scripts/collect.py
research/scripts/make_figures.py
research/scripts/svgchart.py
src/strands_decider/__init__.py
src/strands_decider/cli.py
src/strands_decider/distributed.py
src/strands_decider/evaluate.py
src/strands_decider/hf_export.py
src/strands_decider/infer.py
src/strands_decider/modeling.py
src/strands_decider/mps_kernels.py
src/strands_decider/prompting.py
src/strands_decider/schema.py
src/strands_decider/server.py
src/strands_decider/train.py
src/strands_decider.egg-info/PKG-INFO
src/strands_decider.egg-info/SOURCES.txt
src/strands_decider.egg-info/dependency_links.txt
src/strands_decider.egg-info/entry_points.txt
src/strands_decider.egg-info/requires.txt
src/strands_decider.egg-info/scm_file_list.json
src/strands_decider.egg-info/top_level.txt
src/strands_decider/data/__init__.py
src/strands_decider/data/adequacy.py
src/strands_decider/data/catchall.py
src/strands_decider/data/collate.py
src/strands_decider/data/distill.py
src/strands_decider/data/format.py
src/strands_decider/data/generated.py
src/strands_decider/data/multistep.py
src/strands_decider/data/policy.py
src/strands_decider/data/question_transforms.py
src/strands_decider/data/recipes.py
src/strands_decider/data/replay.py
src/strands_decider/data/sampling.py
src/strands_decider/data/shards.py
src/strands_decider/data/synth.py
src/strands_decider/data/synth_pairs.py
src/strands_decider/data/teacher.py
tests/conftest.py
tests/test_adequacy.py
tests/test_catchall.py
tests/test_checkpoint_load.py
tests/test_cli_build.py
tests/test_configs.py
tests/test_core.py
tests/test_data_identity.py
tests/test_ddp.py
tests/test_distill.py
tests/test_engine_dtype.py
tests/test_generated.py
tests/test_gpu_smoke.py
tests/test_hf_export.py
tests/test_hybrid.py
tests/test_llm_client.py
tests/test_mps_kernels.py
tests/test_multistep.py
tests/test_policy.py
tests/test_prefix_cache.py
tests/test_question_transforms.py
tests/test_run_recipe.py
tests/test_sampling.py
tests/test_server.py
tests/test_teacher.py
tests/fixtures/v19-p5-run1/hobson_config.json
tests/fixtures/v19-p5-run1/train_config.json
training/AGENTS.md
training/README.md
training/hardware.md
training/legacy-v7.md
training/recipe.sh
training/recipe_v7.sh
training/run_recipe.sh
training/steps.md
training/aws/README.md
training/aws/image/setup-host.sh
training/aws/image/verify-host.sh
training/aws/scripts/.gitignore
training/aws/scripts/common.sh
training/aws/scripts/ensure-infra.sh
training/aws/scripts/launch-capacity-block.sh
training/aws/scripts/launch-host.sh
training/aws/scripts/ssm-run.sh
training/aws/scripts/sync-code.sh
training/aws/scripts/teardown.sh