Codeseys
/

composer-replication-framework

Reinforcement Learning

Model card Files Files and versions

composer-replication-framework / composer_replication /datagen

Commit History

Wave 21: adversarial-review fixes — all 9 verified findings closed

3bbcf21

Baladithya Balamurugan Claude Fable 5 commited on 11 days ago

Wave 21: Stage-0 dataset pipeline — swesmith engine, rollout harness, gates, contract

9a2ce20

Baladithya Balamurugan Claude Fable 5 commited on 11 days ago

Wave 20: Tier-0 fidelity fixes — k1-in-reward KL + Composer-2 behavior rewards

41289bf

Baladithya Balamurugan Claude Opus 4.8 (1M context) commited on 11 days ago

R14: harden live-Docker tests against transient daemon contention

c647fe9

Baladithya Balamurugan Claude Opus 4.8 (1M context) commited on 12 days ago

Wave 2: 4 new modules (kill-switch, EKS/SageMaker executors, DockerSandbox) + B4/B7 completion

7a55e1e

Baladithya Balamurugan Claude Opus 4.8 (1M context) commited on 12 days ago

fix(phase-8): close all 5 cross-family final-verify findings + regression tests

678d10b

Codeseys commited on 22 days ago

feat(b4-gpu+b6): GPU train-proof on A10G + docker-gated substrate E2E test

c009712

Codeseys commited on 22 days ago

feat(wave-a): close ADR-011 (SDPO alignment indices) + ADR-012 (review findings)

d02d724

Codeseys commited on 22 days ago

review+fix: cross-family adversarial ADR review (owed item) + remediation

185cce2

Codeseys commited on 22 days ago

feat(datagen): ADR-010 FeatureDeletionEnv synthetic-data subsystem; accepted

9336af3

Codeseys commited on 23 days ago