Stabilize wrapped Laplace PDFs for extreme skew

[FlorianPfaff]

Bug

WrappedLaplaceDistribution.pdf(...) formed the skew mixture as

(positive_component + kappa**2 * negative_component) / (1 + kappa**2)

For a large but finite skew parameter, kappa**2 can overflow even though the normalized density is finite. For example, lambda_=1 and kappa=1e200 should be close to the uniform density, but the previous implementation raises under strict NumPy overflow handling (or produces non-finite intermediate values otherwise).

Fix

Evaluate the same normalized mixture in a scale-free form:

• for kappa <= 1, retain the direct kappa * kappa weighting;
• for kappa > 1, divide numerator and denominator by kappa**2 and use (1 / kappa) * (1 / kappa).

This avoids squaring a large skew parameter while preserving the ordinary parameter path.

Regression coverage

Add a NumPy regression with kappa=1e200 under strict overflow, invalid, and divide handling. It verifies that the PDF remains finite and approaches 1 / (2*pi) rather than failing during mixture normalization.

Validation

• reproduced the old overflow encountered in square failure;
• verified the scale-free calculation returns finite values for two query points;
• branch comparison: 2 commits ahead and 0 behind main;
• diff is limited to 30 implementation-line changes and an 18-line focused regression.

GitHub Actions is authoritative for the full backend, lint, packaging, documentation, and integration matrix.

[github-actions]

✅MegaLinter analysis: Success

Descriptor	Linter	Files	Fixed	Errors	Warnings	Elapsed time
✅ COPYPASTE	jscpd	yes		no	no	28.62s
✅ JSON	prettier	7	0	0	0	1.23s
✅ JSON	v8r	7		0	0	4.57s
✅ MARKDOWN	markdownlint	68	0	0	0	1.97s
✅ MARKDOWN	markdown-table-formatter	68	0	0	0	0.48s
✅ PYTHON	black	1865	88	0	0	100.73s
✅ PYTHON	isort	1865	140	0	0	2.86s
✅ REPOSITORY	betterleaks	yes		no	no	2.46s
✅ REPOSITORY	checkov	yes		no	no	54.07s
✅ REPOSITORY	gitleaks	yes		no	no	18.33s
✅ REPOSITORY	git_diff	yes		no	no	0.25s
✅ REPOSITORY	secretlint	yes		no	no	87.58s
✅ REPOSITORY	syft	yes		no	no	6.15s
✅ REPOSITORY	trivy-sbom	yes		no	no	6.4s
✅ REPOSITORY	trufflehog	yes		no	no	33.25s
✅ YAML	prettier	11	0	0	0	0.7s
✅ YAML	v8r	11		0	0	13.18s
✅ YAML	yamllint	11		0	0	0.66s

Notices

📣 MegaLinter 9.5.0 is out! Discover the new features and security recommendations in the release announcement. (Skip this info by defining SECURITY_SUGGESTIONS: false)

See detailed reports in MegaLinter artifacts

Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining FLAVOR_SUGGESTIONS: false)

• Documentation: Custom Flavors
• Command: npx mega-linter-runner@9.6.0 --custom-flavor-setup --custom-flavor-linters PYTHON_BLACK,PYTHON_ISORT,COPYPASTE_JSCPD,JSON_V8R,JSON_PRETTIER,MARKDOWN_MARKDOWNLINT,MARKDOWN_MARKDOWN_TABLE_FORMATTER,REPOSITORY_CHECKOV,REPOSITORY_GIT_DIFF,REPOSITORY_GITLEAKS,REPOSITORY_BETTERLEAKS,REPOSITORY_SECRETLINT,REPOSITORY_SYFT,REPOSITORY_TRIVY_SBOM,REPOSITORY_TRUFFLEHOG,YAML_PRETTIER,YAML_YAMLLINT,YAML_V8R

Show us your support by starring ⭐ the repository