V133 verified mathematical evidence residual #2
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Trace Ace V133 Verified Math Evidence | |
| on: | |
| pull_request: | |
| branches: [agent/v132-nested-applicability-gate] | |
| paths: | |
| - 'competitions/trace_the_ace/v133_verified_math_evidence.py' | |
| - '.github/workflows/trace-ace-v133-verified-math-evidence.yml' | |
| workflow_dispatch: | |
| env: | |
| PREPARED_RUN_ID: 32400309220 | |
| jobs: | |
| evaluate: | |
| runs-on: ubuntu-24.04 | |
| timeout-minutes: 30 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.12' | |
| cache: pip | |
| - name: Install dependencies | |
| run: python -m pip install --disable-pip-version-check numpy scipy scikit-learn pandas | |
| - name: Restore frozen transcript archive from GitHub cache only | |
| id: transcript-cache | |
| uses: actions/cache@v4 | |
| with: | |
| path: transcripts.zip | |
| key: trace-ace-transcripts-v1-603547640 | |
| - name: Require exact cache hit | |
| run: | | |
| test '${{ steps.transcript-cache.outputs.cache-hit }}' = 'true' | |
| test "$(stat -c%s transcripts.zip)" = '603547640' | |
| echo 'e685b85b04694e130c25b17d09cdd1892fbda5e9fa685e98b2300114b915aa2d transcripts.zip' | sha256sum -c - | |
| - name: Download exact frozen prepared artifact | |
| uses: actions/download-artifact@v4 | |
| with: | |
| name: v121-prepared | |
| path: v121_prepared | |
| repository: heathsanchez/mathgraph | |
| run-id: ${{ env.PREPARED_RUN_ID }} | |
| github-token: ${{ github.token }} | |
| - name: Verify frozen sample | |
| run: grep -q 'b1612f9fe4558680e468afb2a2452b75c603c244934fe62f7345feee68a61bc1' v121_prepared/manifest.json | |
| - name: Run frozen V133 | |
| run: python competitions/trace_the_ace/v133_verified_math_evidence.py --archive transcripts.zip --dir v121_prepared --out v133_verified_math_evidence.json | |
| - name: Show decision | |
| if: always() | |
| run: cat v133_verified_math_evidence.json | |
| - uses: actions/upload-artifact@v4 | |
| if: always() | |
| with: | |
| name: trace-ace-v133-verified-math-evidence | |
| path: v133_verified_math_evidence.json | |
| retention-days: 14 |