CITATION.cff
LICENSE
MANIFEST.in
Makefile
README.md
constraints-cpu-py310-tested.txt
constraints-train-recorded.txt
pyproject.toml
requirements-gpu-py310-cu124.txt
assets/verified-support-story.png
configs/drgrpo_countdown_05b.json
configs/drgrpo_graph_coloring_05b.json
configs/drgrpo_mathir_05b.json
configs/drgrpo_pantry_plan_05b.json
configs/drgrpo_python_factors_05b.json
configs/maxrl_countdown_05b.json
configs/maxrl_graph_coloring_05b.json
configs/maxrl_mathir_05b.json
configs/maxrl_pantry_plan_05b.json
configs/maxrl_python_factors_05b.json
configs/redr_countdown_05b.json
configs/redr_graph_coloring_05b.json
configs/redr_mathir_05b.json
configs/redr_pantry_plan_05b.json
configs/redr_python_factors_05b.json
configs/remax_countdown_05b.json
configs/remax_graph_coloring_05b.json
configs/remax_mathir_05b.json
configs/remax_pantry_plan_05b.json
configs/remax_python_factors_05b.json
evidence/mode_diversity_training.json
evidence/verified_samples_completed_cohort.jsonl.gz
evidence/experiments/catalog_v1.json
evidence/experiments/catalog_v1.sha256
evidence/experiments/historical_bindings_v1.json
evidence/snapshots/level3_comparison_20260917.json
evidence/snapshots/matched_redr_20260924.json
evidence/snapshots/online_rlep_20260927.json
evidence/snapshots/replay_mechanism_ladder_20260924.json
evidence/snapshots/tuned_control_stage2_20260927.json
evidence/snapshots/tuned_control_sweep_20260927.json
examples/api_walkthrough.py
examples/prepare_training_walkthrough.py
examples/replay_loss.py
ops/__init__.py
ops/audit_gpu_smoke.py
ops/build_mode_diversity_training.py
ops/check_training_reference.py
ops/compare_gpu_recipe.py
ops/export_experiment_packages.py
ops/followup_metrics.py
ops/gpu_smoke.py
ops/profile_replay.py
ops/repo_env.sh
ops/reproduce_training.py
ops/resume_gpu.py
ops/run_recipe.py
ops/setup_gpu_environment.sh
ops/summarize_performance.py
ops/train.sh
ops/verify_release.py
src/build_support.py
src/remax/__init__.py
src/remax/__main__.py
src/remax/actor.py
src/remax/admission_retention.py
src/remax/answer_options.py
src/remax/args.py
src/remax/benchmark.py
src/remax/benchmark_identity.py
src/remax/canonical_actions.py
src/remax/canonical_replay.py
src/remax/checkpointing.py
src/remax/cli.py
src/remax/dapo.py
src/remax/fused_adam_shim.py
src/remax/gapo.py
src/remax/input_identity.py
src/remax/input_registry_v1.json
src/remax/launch_record.py
src/remax/launcher.py
src/remax/legacy_modebench.py
src/remax/logging_utils.py
src/remax/math_grader.py
src/remax/math_grader_process.py
src/remax/math_grader_worker.py
src/remax/math_route.py
src/remax/math_strategy_canonicalizer.py
src/remax/math_strategy_menu.py
src/remax/maxent_controllers.py
src/remax/maxent_length_controller.py
src/remax/maxrl.py
src/remax/modebench_guided.py
src/remax/modebench_release_v1.json
src/remax/on_policy_maxent.py
src/remax/online_canonical_bank.py
src/remax/online_canonical_controller.py
src/remax/outcome_collision.py
src/remax/proposal_starvation.py
src/remax/py.typed
src/remax/recipe_types.py
src/remax/recipes.py
src/remax/replicated_group.py
src/remax/results.py
src/remax/resume_state.py
src/remax/rlep.py
src/remax/runtime.py
src/remax/scoring.py
src/remax/seed_weights.py
src/remax/semantic_rms_controller.py
src/remax/semantic_shannon.py
src/remax/setpo.py
src/remax/setpo_embedder.py
src/remax/tensor_utils.py
src/remax/train_zero_math.py
src/remax/trajectory_dataset.py
src/remax/ucpo.py
src/remax/verified_route_library.py
src/remax/verified_transformations.py
src/remax/vllm_worker.py
src/remax/walkthrough.py
src/remax/xdr.py
src/remax/xdr_sac_dual_controller.py
src/remax/xdr_tau_controller.py
src/remax/core/__init__.py
src/remax/core/admission.py
src/remax/core/bank.py
src/remax/core/bank_state.py
src/remax/core/bank_types.py
src/remax/core/checkpoints.py
src/remax/core/execution.py
src/remax/core/metrics.py
src/remax/core/objectives.py
src/remax/core/replay_types.py
src/remax/core/scheduling.py
src/remax/core/scoring.py
src/remax/experiments/__init__.py
src/remax/experiments/dapo.py
src/remax/experiments/gapo.py
src/remax/experiments/on_policy_maxent.py
src/remax/experiments/outcome_collision.py
src/remax/experiments/replay_objectives.py
src/remax/experiments/rlep.py
src/remax/experiments/seed_weights.py
src/remax/experiments/semantic_shannon.py
src/remax/experiments/setpo.py
src/remax/experiments/setpo_embedder.py
src/remax/experiments/ucpo.py
src/remax/experiments/xdr.py
src/remax/experiments/oat/__init__.py
src/remax/experiments/oat/grpo.py
src/remax/experiments/oat/initialization.py
src/remax/experiments/oat/run.py
src/remax/integrations/__init__.py
src/remax/integrations/oat/__init__.py
src/remax/integrations/oat/admission.py
src/remax/integrations/oat/checkpoints.py
src/remax/integrations/oat/data.py
src/remax/integrations/oat/dispatch.py
src/remax/integrations/oat/evaluation.py
src/remax/integrations/oat/grpo.py
src/remax/integrations/oat/initialization.py
src/remax/integrations/oat/lifecycle.py
src/remax/integrations/oat/policy.py
src/remax/integrations/oat/progress.py
src/remax/integrations/oat/replay.py
src/remax/integrations/oat/runner.py
src/remax/integrations/oat/sampling.py
src/remax/integrations/oat/scoring.py
src/remax/integrations/oat/selection.py
src/remax/integrations/oat/support.py
src/remax/integrations/oat/sync.py
src/remax/integrations/oat/telemetry.py
src/remax/integrations/oat/update.py
src/remax/learner/__init__.py
src/remax/learner/base.py
src/remax/learner/grpo.py
src/remax/learner/init.py
src/remax/learner/run.py
src/remax_rl.egg-info/PKG-INFO
src/remax_rl.egg-info/SOURCES.txt
src/remax_rl.egg-info/dependency_links.txt
src/remax_rl.egg-info/entry_points.txt
src/remax_rl.egg-info/requires.txt
src/remax_rl.egg-info/top_level.txt
tests/__init__.py
tests/boundary_runtime_harness.py
tests/compare_training_runs.py
tests/conftest.py
tests/distributed_harness.py
tests/resume_harness.py
tests/test_admission_retention.py
tests/test_benchmark_boundary.py
tests/test_canonical_actions.py
tests/test_canonical_replay.py
tests/test_comparisons.py
tests/test_evaluation_failure_boundary.py
tests/test_execution_resources.py
tests/test_gpu_workflow.py
tests/test_maxrl.py
tests/test_on_policy_maxent.py
tests/test_online_canonical_bank.py
tests/test_package_contract.py
tests/test_public_walkthrough.py
tests/test_published_boundary.py
tests/test_refactor_audit.py
tests/test_release_recipes.py
tests/test_replay_architecture.py
tests/test_replicated_group.py
tests/test_result_packages.py
tests/test_resume_audit.py
tests/test_resume_equivalence.py
tests/test_seed_weights.py
tests/test_strict_recipes.py
tests/test_training_conformance.py
tests/test_training_reference_guard.py
tests/test_verifier_workers.py
tests/training_harness.py
tests/training_oracle.py
tests/fixtures/benchmark_boundary_v1.json
tests/fixtures/benchmark_boundary_v1.sha256
tests/fixtures/gpu_historical_pantry_v1.json
tests/fixtures/gpu_historical_pantry_v1.sha256
tests/fixtures/training_v1/expected.json
tests/fixtures/training_v1/inputs.json
tests/fixtures/training_v1/manifest.json
tests/installed/smoke.py