Skip to content

Merlin-Arthur pipeline (persistent) - #508

Draft
AuguB wants to merge 86 commits into
mainfrom
trace/ma-pipeline
Draft

Merlin-Arthur pipeline (persistent)#508
AuguB wants to merge 86 commits into
mainfrom
trace/ma-pipeline

Conversation

@AuguB

@AuguB AuguB commented Jul 22, 2026

Copy link
Copy Markdown
Contributor

Persistent branch baked into the shiraz image for the Merlin-Arthur pipeline. Based on merlin_arthur_reasoning_fix.

Made with Cursor

Sibling PRs: merlin-arthur Aleph-Alpha-Research/merlin-arthur#393, eval-framework #508, shiraz Aleph-Alpha-Research/shiraz#1016, prey Aleph-Alpha-Research/prey#705, metal-tiger Aleph-Alpha-Research/metal-tiger#971, savanna Aleph-Alpha-Research/savanna#3164

AuguB and others added 30 commits June 24, 2026 12:14
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: prabhuteja12 <11191577+prabhuteja12@users.noreply.github.com>
Co-authored-by: Martin Reinhardt <martin.reinhardt@aleph-alpha.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
…24 (#415)

Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: prabhuteja12 <11191577+prabhuteja12@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
pacman82 and others added 30 commits July 20, 2026 14:14
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: fsschneider <12153723+fsschneider@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
…473)

Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: prabhuteja12 <11191577+prabhuteja12@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
…477)

Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
…29 (#478)

Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: aar-public-version-bump-bot[bot] <286693160+aar-public-version-bump-bot[bot]@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

# Conflicts:
#	.github/workflows/claude-code-review.yaml
#	.github/workflows/generate_task_docs.yml
#	.github/workflows/renovate.yaml
#	.github/workflows/tests.yml
#	.release-please-manifest.json
#	CHANGELOG.md
#	THIRD_PARTY.md
#	THIRD_PARTY_LICENSES.md
#	docs/tasks/README.md
#	pyproject.toml
#	src/eval_framework/tasks/base.py
#	src/eval_framework/tasks/benchmarks/squad.py
#	src/eval_framework/tasks/registry.py
#	src/eval_framework/tasks/task_names.py
#	uv.lock
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.

7 participants