Spaces:

v4xsh
/

nervousystem-env

Running

App Files Files Community

nervousystem-env / scripts

93.3 kB

Ctrl+K

Ctrl+K

3 contributors

History: 11 commits

vx7sh's picture

docs: publish real SFT log_history and add provenance note

1a3f787 25 days ago

evaluate.py

27.5 kB
docs(evidence): add multi-agent eval, long-horizon trace, and constrained eval logs 25 days ago
evaluate_model.py

17 kB
fix(eval): add phase-aware hard and cascade action selection 25 days ago
evaluate_multi_agent.py

4.43 kB
docs(evidence): add multi-agent eval, long-horizon trace, and constrained eval logs 25 days ago
exploit_test.py

4.42 kB
test(reward): make reward audit run in-process when server is offline 25 days ago
generate_long_horizon_trace.py

4.71 kB
docs(evidence): add multi-agent eval, long-horizon trace, and constrained eval logs 25 days ago
plot_final_evidence.py

13.5 kB
docs: publish real SFT log_history and add provenance note 25 days ago
reward_audit.py

14.5 kB
test(reward): make reward audit run in-process when server is offline 25 days ago
run_overnight.sh

2.86 kB
feat(rl): GRPO continuation from SFT adapter with multi-step task rollouts 25 days ago
seed_variance.py

4.52 kB
feat(eval): add seed variance reporting script 25 days ago