Commit History

Add E2E Structures tab
e1309c3
verified

timchen0618 commited on

Fix Baseline A/B/C sidebar rendering; rename to 'structure per q' / 'structure per ds' / 'DCI'; add e2e as 7th config in Compare
951b98b
verified

timchen0618 commited on

Add 4 MoNaCo-parity tabs: Unified eval, Eval Structures v0, Baseline A/B/C trajectories, Compare
bba5457
verified

timchen0618 Copilot commited on

Add E2E Trajectories view: agent traj + per-qid F1/EM for wiki_opentable e2e run
998699e
verified

timchen0618 Copilot commited on

Initial: Open-WikiTable test split viewer (6,602 qids)
2da3a94
verified

timchen0618 Copilot commited on