Spaces:
Running
Running
Commit History
-
Add E2E v3 + rawtext views
Verified signatureAdd the production overlay trajectory with canonical answer-F1 scoring to run and Compare views, plus a structure alias for the cached E2E v3 scaffold. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: c2fe83fc-cc75-4d0b-b5ba-4a8def928fdc12ea280 -
Add E2E v3 constructed structures tab
Verified signatureAdd compressed per-question E2E v3 structure shards for the canonical size5000/seed1 full dataset and wire the rose-accented structures tab. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: c2fe83fc-cc75-4d0b-b5ba-4a8def928fdcf67cae0
-
Add full-run baseline and E2E tabs
Verified signatureAdds c1, c2, c6 Agentic-DCI, naive-search, E2E v3, and Compare views over the canonical 500-question split. c1/c2 responses include higher-token recovery overlays, and run modes safely lock to the canonical universe. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: c2fe83fc-cc75-4d0b-b5ba-4a8def928fdcc10b0c0
-
Add PhantomWiki viewer (Corpus + Eval tabs; 9 size/seed universes)
Verified signature548b2a6