Commit History

feat: reward verifier alignment, notebook hardening, model name fix
cdc237b
Running

CreativeEngineer Claude Opus 4.6 commited on

docs: align training workflow and plan ssot
e8e5af5

CreativeEngineer commited on

feat: make llm training workflow low-fidelity only
9c3599b

CreativeEngineer commited on

feat: add model-driven llm reward evaluation
ede4c5c

CreativeEngineer commited on

feat: add reward and verifier monitoring telemetry
5e0e606

CreativeEngineer commited on

feat: add llm rollout contract and simplify ppo smoke
ebd0ff3

CreativeEngineer commited on

feat: add low-fi PPO smoke workflow
97fc141

CreativeEngineer commited on

docs: codify multifidelity training policy
513a2e2

CreativeEngineer commited on

docs: require trained policy evidence
27d58b3

CreativeEngineer commited on

docs: sync status trackers to verifier state
ba716cf

CreativeEngineer commited on

chore: add hackathon repo guardrails
98ffb4a

CreativeEngineer commited on

chore: scaffold fusion design lab repo
65b799e

CreativeEngineer commited on