Skip to content

Refreeze manuscript on the 32-model board - #157

Merged
MaxGhenis merged 3 commits into
mainfrom
refreeze-32-model
Aug 23, 2026
Merged

Refreeze manuscript on the 32-model board#157
MaxGhenis merged 3 commits into
mainfrom
refreeze-32-model

Conversation

@MaxGhenis

Copy link
Copy Markdown
Contributor

Re-freezes paper/snapshot/20260501 on the 32-model dashboard-data-20260822 board (recombination sha verified: b883ec66…).

  • Roster 30 → 32 throughout; Table 2 rebuilds from the registry and cards with the two new rows (grok-4.6; ox-alpha with the OpenRouter stealth provider id and its 2026-08-21 listing date, explained in the caption).
  • One sentence in the roster description states that one row is a cloaked preview model listed as such.
  • MODEL_RELEASE_DATES gains grok-4.6 and ox-alpha (the table raised a KeyError without them); display names added.
  • Parse-failure counts recompute from the artifact: 629 of 63,488 cells, 1.0%.
  • Rendered HTML + PDF re-pinned. Table 2 read visually across pages 9–13: no clipping, both new rows correct.

Sol authored the freeze and source updates via carpool; its sandbox could not run Quarto (socket restriction), so the render, the release-date entries, a caption fix (footnote syntax inside a LaTeX caption fails the PDF build), and a tense fix are mine. Suite 575 passed.

🤖 Generated with Claude Code

MaxGhenis and others added 3 commits August 23, 2026 03:57
…on fix

Adds grok-4.6 and ox-alpha to MODEL_RELEASE_DATES (the table
rendered a KeyError without them), folds the Ox Alpha note into the
Table 2 caption as plain text (a footnote inside a LaTeX caption fails
the PDF build), fixes the preview-row sentence to present tense, and
re-pins the rendered-paper hashes.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@vercel

vercel Bot commented Aug 23, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
policybench-site Ready Ready Preview Aug 23, 2026 2:11am

Request Review

@MaxGhenis
MaxGhenis merged commit ff1a009 into main Aug 23, 2026
5 of 6 checks passed
@MaxGhenis
MaxGhenis deleted the refreeze-32-model branch August 23, 2026 02:11
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant