メニュー
Build all paper figures and tables from registered runs and verify claim coverage.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Build, refresh, or promote rows from `docs/initialDocs/derivedBibliography.md` — the auto-generated catalogue of references cited by the papers under `literature/papers/`. Use when the user asks to "extract references", "build the derived bibliography", "refresh derived refs", "what does paper X cite", "promote this derived ref to the main bibliography and download it", or to scan/aggregate citations from the local PDFs. Also: every time a new paper folder lands on disk, this refresh has to run so the derived list stays current.
Build the GPU Docker image and validate the runtime environment.
Build a dataset manifest and validate it against the manifest schema.
Run an ablation grid and aggregate the results.
Run the end-to-end smoke pipeline (dummy model on the synthetic smoke dataset).
Add a single new paper or repository to docs/initialDocs/revisedBibliography.md and, when possible, materialise its `literature/papers/<slug>/` folder (PDF + shallow-cloned repo + notes.md + citation.bib) following docs/initialDocs/bibliographySpec.md. The folder is created only when at least one artefact (PDF or repo) was downloaded AND year + first author are known; otherwise the row is added with an empty Literature dir cell. Use when the user pastes a URL, BibTeX, or arXiv ID and asks to "add this paper", "save this reference", "track this in the bibliography", etc.
SOC 職業分類に基づく
| name | build-paper-artifacts |
| description | Build all paper figures and tables from registered runs and verify claim coverage. |
The paper artifact build is fully script-driven. No artifact in paper/figures/ or paper/tables/ may be edited by hand.
Steps:
reports/claim_to_evidence_matrix.md has a registered run. Reject if any claim is missing evidence.python scripts/build_paper_artifacts.py \
--runs experiments/runs \
--registry experiments/registry \
--out paper
python scripts/check_markdown_links.py paper
make validate-schemas
Do not generate any artifact from in-memory state — every figure and table reads from saved predictions.