v1.3.0 — the method-coverage release

Closes every method-coverage gap listed in the v1.2 roadmap. 16 runnable demos, 68 numeric-check assertions, 46 Crossref-verified references, 51 validated tool bindings, 246 unit tests — all CI-enforced.

Five new numeric-contract demos

Demo	The point it pins numerically
randomization-inference-demo/	Robust-SE t-tests over-reject under concentrated leverage; the Fisher randomization test has exact size and retains power (Young 2019)
qte-demo/	A null ATE hiding large distributional effects; quantile regression recovers the analytic QTE curve (Koenker-Bassett 1978)
lp-did-demo/	Pooled TWFE event studies contaminated under staggered adoption; LP-DiD with clean controls recovers the true dynamic path (Dube-Girardi-Jordà-Taylor)
bunching-demo/	Excess mass at a tax kink identifies the earnings elasticity (Saez 2010), with oracle-vs-feasible counterfactuals and two falsification worlds
matrix-completion-demo/	DiD structurally biased under interactive fixed effects; low-rank imputation recovers the truth — rank-sensitivity caveat demonstrated, not hidden (Athey et al. 2021)

Also in this release

• StatsPAI tool registry expanded 43 → 51 validated bindings (lp_did, ri_test, qte, bunching, notch, matrix_completion, interactive_fe, aipw), hub kept in sync by the registry gate.
• Methods reference & glossary coverage for all five methods.
• Launch kit (docs/launch-kit/) with bilingual announcement drafts and awesome-list blurbs; .zenodo.json for DOI minting.

Full details in CHANGELOG.md.

🤖 Generated with Claude Code

v1.2.0 — the verifiability release

The theme of v1.2 is verifiability: every discipline the skills impose on a manuscript is machine-enforced on the repository itself first — and the enforcement tooling is itself tested.

Highlights

• Unit-tested quality tooling — 246 hermetic pytest tests under tests/ covering the validator, citation verifier, skill auditor, smoke runner, numeric-check protocol, scaffolder, and installer (make test, ~5s, no network).
• Quality scorecard — make scorecard regenerates docs/quality-scorecard.md from measured state; preflight fails when the committed page drifts from reality.
• Double machine learning demo — examples/dml-plr-demo/ pins the Chernozhukov et al. (2018) contrast to known targets: linear-controls OLS biased upward, the non-orthogonal ML plug-in attenuated at exactly var(v)/var(D)·θ, DML partialling-out on the truth with honest coverage. Five NUMERIC-CHECK assertions, numpy-only.
• End-to-end walkthrough — examples/end-to-end-walkthrough.md traces one fictional paper through all 12 workflow steps, naming the skill, the gate, and the artifact at each.
• Three-job CI — structural validation (+ offline citation gate + prose groundedness gate), unit tests, and every Python demo run under the numeric-check contract with --strict-deps.
• Pinned stack actually installs — the very first CI run of the new smoke gate caught phantom pins that had never been installable from PyPI (linearmodels==6.6, econtools==0.3.5, a polars conflict). Repaired and verified in a clean Python 3.12 environment: 11 demos, 47 numeric checks green.
• Release hygiene — CHANGELOG.md (back-filled to v1.0.0), CITATION.cff, docs/roadmap.md with the operating definition of the reference automated-empirics repo, bilingual README upgrade (CI badge, honest comparison table).

Full details in CHANGELOG.md.

🤖 Generated with Claude Code