Codeseys
/

composer-replication-framework

Reinforcement Learning

Model card Files Files and versions

composer-replication-framework / docs

Ctrl+K

Ctrl+K

4 contributors

History: 7 commits

Codeseys's picture

Wave 12: close V1-V8 brief — GPU smoke, SDPO firing, real-trace e2e

d88715c about 2 months ago

adrs
Wave 11: cross-model adversarial review + honest down-revision about 2 months ago
research
Wave 11: cross-model adversarial review + honest down-revision about 2 months ago
COMPOSER_RECIPE_MAPPING.md

16 kB
Integrate Cursor blog directly + audit research note + add SDPO/OPSD link about 2 months ago
DEEP_WORK_LOOP_LOG.md

1.98 kB
Wave 7: Phase 2-4 of deep work loop — backlog, parallel research, three ADRs about 2 months ago
HF_REPO_LAYOUT.md

3.23 kB
Initial commit: Composer 2.5 Replication Framework — research synthesis about 2 months ago
INTEGRATION_ARCHITECTURE.md

30.6 kB
Wave 3: integration architecture + spike-005 trainer skeleton (16 tests pass) about 2 months ago
METHODOLOGY.md

6.27 kB
Initial commit: Composer 2.5 Replication Framework — research synthesis about 2 months ago
V1_V8_COVERAGE.md

9.6 kB
Wave 12: close V1-V8 brief — GPU smoke, SDPO firing, real-trace e2e about 2 months ago
V3_SUBSTRATE_COVERAGE.md

6.96 kB
Wave 12: close V1-V8 brief — GPU smoke, SDPO firing, real-trace e2e about 2 months ago
VISION_VALIDATION.md

35.5 kB
Wave 12: close V1-V8 brief — GPU smoke, SDPO firing, real-trace e2e about 2 months ago