Skip to content

Lucasuiii/modeling-workbench / .agents/skills/cumcm-workflow

cumcm-workflow

Verified

Build or resume mathematical-modeling competition work, including CUMCM, MCM/ICM, graduate and regional contests, data challenges, and open-topic statistical modeling. Guide problem framing, modeling, computation, validation, Chinese or English LaTeX writing, and reviewed PDF/source delivery using current official requirements. Not for ordinary paper polishing.

FileKindSize
SKILL.mdskill md9.0 KB
agents/openai.yamlconfig427 B
assets/latex-template/generic-ctex/macros.texother859 B
assets/latex-template/generic-ctex/main.tex.tmplother2.5 KB
assets/latex-template/generic-ctex/metadata.tex.tmplother272 B
assets/latex-template/generic-ctex/planned-section.tex.tmplother1.0 KB
assets/latex-template/generic-ctex/references.bibother155 B
assets/latex-template/generic-ctex/sections/00_abstract.texother935 B
assets/latex-template/generic-ctex/sections/98_references.texother221 B
assets/latex-template/generic-ctex/sections/99_appendix.texother264 B
assets/latex-template/generic-ctex/template.jsonconfig304 B
assets/latex-template/generic-en/macros.texother868 B
assets/latex-template/generic-en/main.tex.tmplother2.2 KB
assets/latex-template/generic-en/metadata.tex.tmplother278 B
assets/latex-template/generic-en/planned-section.tex.tmplother1013 B
assets/latex-template/generic-en/references.bibother155 B
assets/latex-template/generic-en/sections/00_abstract.texother454 B
assets/latex-template/generic-en/sections/98_references.texother201 B
assets/latex-template/generic-en/sections/99_appendix.texother240 B
assets/latex-template/generic-en/template.jsonconfig249 B
assets/latex-template/huawei-ctex/main.tex.tmplother3.3 KB
assets/latex-template/huawei-ctex/template.jsonconfig276 B
assets/plot-style/cumcm.mplstyleother953 B
references/01-intake.mdmarkdown3.9 KB
references/02-problem-analysis.mdmarkdown2.8 KB
references/03-model-design.mdmarkdown7.6 KB
references/04-computation.mdmarkdown13.4 KB
references/05-validation.mdmarkdown5.9 KB
references/06-paper-writing.mdmarkdown14.3 KB
references/07-compile-delivery.mdmarkdown6.1 KB
references/artifact-contracts.mdmarkdown3.1 KB
references/competition-adaptation.mdmarkdown6.8 KB
references/competition-writing.mdmarkdown5.6 KB
references/diagnostics.mdmarkdown4.5 KB
references/evidence-rules.mdmarkdown1.6 KB
references/handoffs.mdmarkdown3.5 KB
references/huawei-delivery.mdmarkdown10.1 KB
references/latex-template.mdmarkdown6.2 KB
references/mechanism-validation.mdmarkdown11.6 KB
references/open-topic-research.mdmarkdown4.9 KB
references/task-driven-modeling.mdmarkdown7.2 KB
schemas/claim-ledger.schema.jsonconfig5.5 KB
schemas/common.schema.jsonconfig2.5 KB
schemas/compile-receipt.schema.jsonconfig3.7 KB
schemas/cross-question-ledger.schema.jsonconfig1.3 KB
schemas/delivery-manifest.schema.jsonconfig7.9 KB
schemas/figure-manifest.schema.jsonconfig1.9 KB
schemas/handoff.schema.jsonconfig2.1 KB
schemas/independent-review-package.schema.jsonconfig3.4 KB
schemas/independent-review-result.schema.jsonconfig4.0 KB
schemas/latex-template-manifest.schema.jsonconfig2.4 KB
schemas/model-contract.schema.jsonconfig5.0 KB
schemas/paper-plan.schema.jsonconfig3.3 KB
schemas/paper-quality-report.schema.jsonconfig5.7 KB
schemas/paper-revision-log.schema.jsonconfig2.2 KB
schemas/paper-visible-text-report.schema.jsonconfig1.6 KB
schemas/problem-facts.schema.jsonconfig1.7 KB
schemas/results-index.schema.jsonconfig1.4 KB
schemas/run-manifest.schema.jsonconfig7.1 KB
schemas/source-manifest.schema.jsonconfig1.9 KB
schemas/task-capabilities.schema.jsonconfig3.9 KB
schemas/workflow-state.schema.jsonconfig2.4 KB
scripts/backend_selection.pyscript6.3 KB
scripts/build_handoff.pyscript20.4 KB
scripts/build_independent_review_package.pyscript14.9 KB
scripts/canonical_evidence.pyscript8.4 KB
scripts/compile_sources.pyscript2.4 KB
scripts/cumcm_check.pyscript2.9 KB
scripts/delivery_archives.pyscript7.0 KB
scripts/doctor.pyscript7.5 KB
scripts/index_result.pyscript10.9 KB
scripts/init_latex_paper.pyscript17.2 KB
scripts/init_project.pyscript11.1 KB
scripts/inventory_artifacts.pyscript4.1 KB
scripts/json_pointer.pyscript1.0 KB
scripts/official_materials.pyscript3.0 KB
scripts/paper_visible_text_check.pyscript5.4 KB
scripts/plan_redo.pyscript18.8 KB
scripts/project_status.pyscript5.8 KB
scripts/provenance.pyscript2.2 KB
scripts/record_compile.pyscript13.2 KB
scripts/record_decision.pyscript12.0 KB
scripts/record_run.pyscript28.1 KB
scripts/refresh_evidence.pyscript4.7 KB
scripts/set_mode.pyscript2.0 KB
scripts/submission_check.pyscript10.6 KB
scripts/workflow_checks.pyscript146.0 KB

references/05-validation.md

View on GitHub
# Validation responsibility

## First review: full and context-separated

Build the current computation handoff, then run:

```bash
python3 "$S/build_independent_review_package.py" --project <project>
```

The package binds only canonical evidence for formal results: official inputs, problem/model contracts, `RESULTS_INDEX.json`, cited successful `official_run: true` manifests, matching source snapshots, formal inputs, claim-bearing outputs, and review instructions. It records `context_excluded` — the prior reasoning it physically left out — rather than asserting that the reviewer holds no conclusions. Failed/exploratory runs, stdout/stderr, full logs, and debug history are excluded; package/upstream freshness digests cover this same canonical set. Stop and route it to a separate task. The builder records the reviewer selection rather than asking the user to confirm it: separation now comes from the block cut itself, since the `computation-validation` handoff carries the task that produced it and `HANDOFF-E010` rejects a review whose `task_ref` matches. The result template ships with every remaining independence field `null`, so the reviewer has to assert them; a null fails `IREVIEW-E027`. Differing task references are a paste guard, not proof of independence. Same-model fresh-context review remains correlated. Task references improve context-separation evidence but cannot cryptographically prove reviewer independence.

The package includes a frozen copy of [mechanism-validation.md](mechanism-validation.md). Read only applicable sections and independently assess the selected checks’ mathematical meaning, tolerance basis and evidence strength, including whether a plausible incorrect implementation could pass. Packaged instructions are bound by the package digest; changing the installed guide alone does not alter historical evidence. Rebuild the package to use revised guidance: the changed digest invalidates the old review result.

## Findings and verdicts

Use the general review criteria in `assets/independent-review/REVIEW_REQUEST.md`: derive risks from the current problem, then check task coverage, model validity, implementation, discriminating evidence and claim scope. Classify by the consequence for the answer: P0 invalidates the answer or delivery; P1 is a material limitation within a supported, task-relevant answer; P2 is an optional improvement. Give concrete evidence for blockers, not a preference for a different model.

A valid proof can support a general claim; finite experiments support only their justified coverage. Scope reduction cannot erase an unanswered requirement. Review a repair's effect on other conclusions, not just the original failing case. Select a few high-value checks appropriate to the problem; no universal experiment checklist is required.

Verdicts are `accepted`, `accepted_with_concerns`, `revision_required`, and `inconclusive`. Only an open P0 permits `revision_required`. Open P1/P2 items remain visible as warnings or suggestions and do not block paper work.

After a full review returns open P0 findings, rerunning the package builder in auto mode defaults to a targeted re-review. It archives the prior review/package and targets every prior open P0. The new package embeds `TARGETED_FINDINGS.json` with only `finding_id`, `category`, `location`, `evidence`, and `recommendation`, so a fresh reviewer can work from the package alone without receiving the full old review. Do not turn unrelated newly noticed P1/P2 items into new blockers. A genuinely new P0 may still require revision.

## The one checkpoint in this block

Before building `validation-paper`, put the conclusions in front of the person and record the answer in `CLAIM_LEDGER.conclusion_check`. This is the cheap place to hear no: a rejection here costs a recomputation, the same rejection at delivery costs a rewritten paper.

Show the claim text, its `scope`, its evidence state, and every open P0/P1 from the review. Do not show run ids, hashes or evidence chains — nobody can audit those by eye, and putting them on the page only dilutes the few things a person can actually judge. `scope` is the one worth reading aloud: it is where a rule that only holds at the point it was derived from becomes visible.

`presented_claim_ids` records what was actually shown. `CLAIM-E023` rejects an acceptance that did not cover every declared claim, so the record cannot say a person approved a conclusion they never saw.

Create `CLAIM_LEDGER.json` from the reviewed evidence. Each paper-bearing claim records its exact text, scope, evidence IDs, evidence state, and limitations. Strong claims—global optimality, equivalence, causality, robustness, significance, or reproducibility—still need claim-specific support. `reproduced` requires an isolated rerun and comparison; an original successful run is only `supported_not_reproduced` unless stronger evidence exists.

Before paper writing, build `validation-paper`. For a targeted result, the builder follows only the structured `previous_review_path` lineage and applies the latest status per finding ID: open/accepted P1 concerns remain, while resolved findings drop out. Its limitations come from supported paper-eligible claim limitations, those current P1 concerns, and explicit model applicability, assumptions, and known limitations—not contradicted/unsupported claims or model `scope`. Its `representation_candidates` proactively identify trend, multi-group comparison, distribution, sensitivity, model-performance, and spatial/network/clustering evidence. A fresh paper task reads this compact handoff first, chooses prose/equation/table/figure, and does not scan full run/debug history.

After the explicit reply, use `record_decision.py --stage validation --decision accepted --confirm-human` with the reply reference and summary (see SKILL.md). It records the existing fields and advances state; paper handoff and initialization reject missing or stale human acceptance.
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall