Spaces:
Running
Running
Commit History
-
Monaco dev viewer — initial 12-tab launch
Verified signature12 tabs: Dataset, Unified eval, 3 baseline agentic trajectories (structure per q / per ds / DCI), 3 e2e_pipeline trajectories (v0/v2/v3), 3 e2e-structures browsers (v0/v2/v3), and 9-cell Compare. Scoring column is the LLM judge_score from submit_judge_responses_aml.py --deterministic-extract (canonical MoNaCo protocol).61b5f50