whestbench 0.4.0__tar.gz

whestbench-0.4.0/.githooks/pre-commit

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# Pre-commit hook: run ruff checks on staged Python files only.
+# Install: git config core.hooksPath .githooks
+#
+# Scope is intentionally narrow (staged files). The pre-push hook runs
+# repo-wide checks; this one is the fast, focused guard against committing
+# ruff drift in the first place.
+
+set -euo pipefail
+
+if ! command -v uv >/dev/null; then
+  echo "[pre-commit] Missing 'uv' in PATH. Install: curl -LsSf https://astral.sh/uv/install.sh | sh" >&2
+  exit 1
+fi
+
+staged_py=$(git diff --cached --name-only --diff-filter=ACMR -- '*.py')
+
+if [ -z "$staged_py" ]; then
+  exit 0
+fi
+
+echo ">>> pre-commit: ruff on staged Python files"
+
+echo "==> ruff check"
+echo "$staged_py" | xargs uv run ruff check
+
+echo "==> ruff format --check"
+echo "$staged_py" | xargs uv run ruff format --check
+
+echo "==> pre-commit checks passed"

whestbench-0.4.0/.githooks/pre-push

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+# Pre-push hook: run local checks that match CI before allowing push.
+# Install: git config core.hooksPath .githooks
+
+set -euo pipefail
+
+run_ci_like_checks() {
+  echo ">>> pre-push: running local checks required before push"
+
+  if ! command -v uv >/dev/null; then
+    echo "[pre-push] Missing 'uv' in PATH. Install with: curl -LsSf https://astral.sh/uv/install.sh | sh" >&2
+    exit 1
+  fi
+
+  echo "==> ruff check"
+  uv run ruff check .
+
+  echo "==> ruff format --check"
+  uv run ruff format --check .
+
+  echo "==> pytest (non-exhaustive)"
+  uv run pytest -m "not exhaustive" -x -q
+
+  echo "==> pre-push checks passed"
+}
+
+run_ci_like_checks

whestbench-0.4.0/.github/workflows/ci.yml

@@ -0,0 +1,94 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies (with latest flopscope)
+        run: uv sync --group dev --upgrade-package flopscope --upgrade-package flopscope-server
+
+      - name: Lint
+        run: uv run ruff check .
+
+      - name: Format check
+        run: uv run ruff format --check .
+
+      - name: Type check
+        run: uv run pyright
+
+      - name: Conventional commits (gitlint)
+        if: github.event_name == 'pull_request'
+        run: uv run gitlint --commits origin/${{ github.base_ref }}..HEAD
+
+      - name: Pre-push hook hint
+        if: failure()
+        run: |
+          cat <<'EOF'
+          ::notice title=Tip: catch this locally before CI::
+          This repo ships pre-commit and pre-push hooks that run ruff (and pytest on push)
+          before each commit/push. If they had been active on your machine, this failure
+          would have been blocked before reaching CI.
+
+          One-time setup per clone:
+
+              git config core.hooksPath .githooks
+
+          After that, every worktree of this clone runs the hooks automatically.
+          See .githooks/pre-commit and .githooks/pre-push for exact commands.
+          EOF
+
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies (with latest flopscope)
+        run: uv sync --group dev --upgrade-package flopscope --upgrade-package flopscope-server
+
+      - name: Test
+        run: uv run pytest -m "not exhaustive" -x -q
+
+  exhaustive-tests:
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies (with latest flopscope)
+        run: uv sync --group dev --upgrade-package flopscope --upgrade-package flopscope-server
+
+      - name: Exhaustive tests
+        run: uv run pytest -m exhaustive -x -q

whestbench-0.4.0/.github/workflows/pypi-publish.yml

@@ -0,0 +1,100 @@
+name: PyPI publish
+
+# Triggered when a `v*` tag is pushed (typically via `cz bump` followed by
+# `git push --follow-tags`). See docs/release-process.md for the
+# end-to-end flow and the one-time PyPI Trusted Publisher setup.
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+# Deny all default permissions; each job opts in to only what it needs.
+permissions: {}
+
+# Never run two publish jobs for the same tag in parallel. Don't cancel an
+# in-flight publish if another tag arrives — let it finish atomically.
+concurrency:
+  group: pypi-publish-${{ github.ref }}
+  cancel-in-progress: false
+
+jobs:
+  build:
+    name: Build sdist + wheel
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Build distributions
+        run: uv build
+
+      - name: Upload dist artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+          if-no-files-found: error
+
+  publish-pypi:
+    name: Publish to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    # The `pypi` environment in repo settings has Required Reviewers
+    # configured, so this job pauses for a human approval before running.
+    environment:
+      name: pypi
+      url: https://pypi.org/project/whestbench/
+    permissions:
+      # Required for Trusted Publishing (OIDC). No long-lived token stored.
+      id-token: write
+    steps:
+      - name: Download dist artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: Create GitHub Release
+    needs: publish-pypi
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Extract CHANGELOG section for this tag
+        run: |
+          # Extract the section between `## v<version>` and the next `## ` header.
+          # commitizen writes headers like `## v0.4.0 (2026-05-26)`.
+          awk -v ver="${GITHUB_REF_NAME}" '
+            $1 == "##" && $2 == ver { capture = 1; next }
+            $1 == "##" && capture { exit }
+            capture { print }
+          ' CHANGELOG.md > release-notes.md
+
+          # Fallback if no matching section (defensive — shouldn't happen if
+          # cz bump was used, but covers manual tags with no changelog entry).
+          if [ ! -s release-notes.md ]; then
+            printf 'Release %s\n\nSee CHANGELOG.md for details.\n' "${GITHUB_REF_NAME}" > release-notes.md
+          fi
+
+          echo "--- release notes ---"
+          cat release-notes.md
+          echo "--- end ---"
+
+      - name: Create GitHub Release
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          gh release create "$GITHUB_REF_NAME" \
+            --title "$GITHUB_REF_NAME" \
+            --notes-file release-notes.md

whestbench-0.4.0/.gitignore

@@ -0,0 +1,250 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# Node (tools/whestbench-explorer)
+node_modules/
+
+# Local git worktrees
+.worktrees/
+
+internal agent config/
+internal codex config/
+.claude/
+.cursor/
+.roo/
+.windsurf/
+internal docs/sanitization/public-sync-state.local.env
+
+# Cloud profiling infrastructure
+profiling/results/*
+!profiling/results/.gitkeep
+profiling/.infra-config.json
+profiling/.lib-cache/
+
+internal config
+
+# Local debug/profiling output
+local-*.html
+local-*.json
+
+# Generated Cython C files
+src/network_estimation/_cython_kernels.c
+
+# Agent-generated plans
+internal docs/
+
+.aicrowd/

whestbench-0.4.0/.gitlint

@@ -0,0 +1,11 @@
+[general]
+contrib=contrib-title-conventional-commits
+# Body content rules don't fit our short, focused commit style.
+ignore=body-is-missing,body-min-length,body-max-line-length
+ignore-merge-commits=true
+
+[contrib-title-conventional-commits]
+types=feat,fix,docs,style,refactor,perf,test,build,ci,chore,revert
+
+[title-max-length]
+line-length=90

whestbench-0.4.0/CHANGELOG.md

@@ -0,0 +1,64 @@
+# Changelog
+
+## Unreleased
+
+## v0.4.0 (2026-05-26)
+
+### Added
+
+- `seed_protocol 3.0` (`whestbench_explicit_per_mlp_seeds`): each MLP's seed is an independent input rather than a derivation from a single root. Each `mlp_seed` value in the parquet column is the canonical input seed. Within-MLP three-stream derivation (weight/sample/estimator) is preserved via `SeedSequence(mlp_seed).spawn(3)`.
+- `whest dataset bake --mlp-seeds FILE` (JSON array of N ints) for explicit per-MLP seeds. Omitting both `--mlp-seeds` and `--seed` auto-generates via `secrets.randbits(63)`.
+- `create_dataset(mlp_seeds=[...])` / `create_dataset_torch(mlp_seeds=[...])`.
+- `MLP.from_row(row, *, seed_protocol_version=...)`: protocol-aware estimator-seed derivation.
+- Frozen fixture `tests/fixtures/single_split_v3_protocol/` for schema-drift regression.
+- Multi-split dataset support: dataset directories can now contain multiple Parquet files in `data/`, one per split, described by an optional `splits:` sub-dict in `metadata.json`. Backward-compatible — single-split datasets are unchanged.
+- `whest dataset combine-splits INPUT_DIR... --output OUTPUT_DIR` CLI subcommand for assembling multi-split datasets from N complete single-split inputs.
+- `whestbench.combine_split_datasets()` Python helper (re-exported from `whestbench`).
+- `whest dataset bake --split <name>` now accepts arbitrary split names matching `[a-z][a-z0-9]*(-[a-z0-9]+)*` (previously restricted to `public` / `holdout`).
+- `whest dataset pull --split <name>` and `whest run --dataset ... --split <name>` for selecting one split from multi-split datasets.
+
+### Changed
+
+- `create_dataset(seed=...)` / `create_dataset_torch(seed=...)` and `whest dataset bake --seed N` now reject with a migration hint pointing at `--mlp-seeds`.
+- Parquet `mlp_seed` column semantics: under 3.0, the column stores the **input** seed (was: derived estimator seed under 2.0). `MLP.seed` (participant-facing) is unchanged across protocols — derived locally from the input under 3.0.
+- `whest dataset inspect` now recognises multi-split datasets and prints a per-split summary, plus the `seed_protocol: <name> (version <version>)` line for all datasets.
+- `whestbench.load_dataset()` returns `Dataset | DatasetDict` based on the dataset shape; explicit `split=` always returns `Dataset`.
+- `whestbench.metadata()` accepts a `DatasetDict` and an optional `split=` filter that projects to single-split-shaped metadata.
+- The dataset-card template gains a multi-split branch with leaderboard-specific wording when splits are `{public, holdout}`; the single-split `public` branch's wording is updated to point at the new evaluation repo.
+
+### Compatibility
+
+- `whestbench.load_dataset` reads both `seed_protocol 2.0` and `3.0` datasets indefinitely. Existing published datasets (e.g. `aicrowd/arc-whestbench-2026-smoke-test`) continue to work unchanged.
+- New bakes only write 3.0.
+- `schema_version` stays at `"3.0"`. The protocol discriminator is `seed_protocol.{name,version}`.
+- The `splits:` field is purely additive.
+- Old whestbench reading new multi-split datasets fails loudly with a missing-`n_mlps` error — upgrade whestbench to read multi-split.
+
+---
+
+## 0.3.0 — 2026-05-25
+
+### BREAKING
+
+- **Dataset format migrated from `.npz` to HF Parquet+sidecar (schema 2.4 → 3.0).**
+  Datasets are now directories with `data/<split>-NNNNN.parquet`, `metadata.json`,
+  and `README.md`. The `whest create-dataset` command is replaced by
+  `whest dataset bake`. The `DatasetBundle` dataclass is removed; internal
+  consumers operate on `datasets.Dataset` directly.
+- **Public estimator interface unchanged.** Estimators still receive `MLP`
+  instances via `predict(mlp: MLP)`.
+
+### NEW
+
+- `whestbench.load_dataset(path_or_repo, revision=..., split=..., token=...)` loads from local directories OR HF Hub.
+- `whestbench.iter_mlps(ds)`, `whestbench.mlp_at(ds, i)`, `whestbench.metadata(ds)`.
+- `whestbench.publish_dataset(local_dir, repo_id=..., tag=..., ...)` for HF Hub uploads.
+- `whestbench.merge_datasets(input_dirs, output_dir=...)` — concatenate partial bakes.
+- `whest dataset {bake, push, pull, merge, inspect}` CLI subcommands.
+- Parallel bake via `--slice K/N` or `--mlp-range START-END` flags; merge with `whest dataset merge`.
+- `whest run --dataset` now accepts HF Hub repos: `hf://owner/repo@v1` (inline revision) or `owner/repo --revision v1`.
+
+### MIGRATION
+
+- Legacy `.npz` datasets cannot be loaded by 0.3.0. Re-bake with `whest dataset bake` at the same `--seed` to reproduce.
+- See `docs/reference/dataset-format.md` for the schema 3.0 specification.

whestbench-0.4.0/PKG-INFO

@@ -0,0 +1,17 @@
+Metadata-Version: 2.4
+Name: whestbench
+Version: 0.4.0
+Requires-Python: >=3.10
+Requires-Dist: datasets>=2.20
+Requires-Dist: faker~=37.0
+Requires-Dist: flopscope>=0.4.1
+Requires-Dist: huggingface-hub>=0.24
+Requires-Dist: jinja2>=3.1
+Requires-Dist: plotext
+Requires-Dist: pyarrow>=14
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich
+Requires-Dist: threadpoolctl>=3.0
+Requires-Dist: tqdm
+Provides-Extra: gpu
+Requires-Dist: torch>=2.1; extra == 'gpu'