Fix infinite log-weight normalization

[FlorianPfaff]

Summary

• Treat positive infinite log weights as dominant support instead of falling back to a uniform distribution.
• Split probability mass uniformly only among hypotheses with +inf log weight.
• Add regression coverage for single and multiple +inf weights and moment matching with a dominant infinite-weight hypothesis.

Bug fixed

normalize_log_weights previously used not np.isfinite(maximum) as a generic fallback to uniform weights. That is appropriate when all weights collapse to -inf/non-finite support, but it is mathematically wrong when one or more hypotheses have +inf log weights: those hypotheses should receive all probability mass. The old behavior could make moment_match_gaussian_hypotheses average incompatible hypotheses even when one hypothesis has an infinite log-score advantage.

Validation

• Branch created from current main (5c989c29fa1d937e3b4b117610f69c7dba018a3d).
• Compared branch against main: 2 commits ahead, 0 behind; only gaussian_hypothesis_mixture.py and its focused tests changed.
• Local pytest was not run because this execution container cannot resolve github.com; repository CI should run the focused regression tests and full matrix.

[github-actions]

✅MegaLinter analysis: Success

Descriptor	Linter	Files	Fixed	Errors	Warnings	Elapsed time
✅ COPYPASTE	jscpd	yes		no	no	53.89s
✅ JSON	prettier	7	0	0	0	0.96s
✅ JSON	v8r	7		0	0	4.99s
✅ MARKDOWN	markdownlint	66	0	0	0	1.95s
✅ MARKDOWN	markdown-table-formatter	66	0	0	0	0.84s
✅ PYTHON	black	766	0	0	0	40.27s
✅ PYTHON	isort	766	0	0	0	2.62s
✅ REPOSITORY	checkov	yes		no	no	46.9s
✅ REPOSITORY	gitleaks	yes		no	no	17.23s
✅ REPOSITORY	git_diff	yes		no	no	0.09s
✅ REPOSITORY	secretlint	yes		no	no	23.52s
✅ REPOSITORY	syft	yes		no	no	4.16s
✅ REPOSITORY	trivy-sbom	yes		no	no	6.97s
✅ REPOSITORY	trufflehog	yes		no	no	23.22s
✅ YAML	prettier	11	0	0	0	0.75s
✅ YAML	v8r	11		0	0	12.68s
✅ YAML	yamllint	11		0	0	0.58s

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@9.5.0 --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_SECRETLINT,REPOSITORY_SYFT,REPOSITORY_TRIVY_SBOM,REPOSITORY_TRUFFLEHOG,YAML_PRETTIER,YAML_YAMLLINT,YAML_V8R

Show us your support by starring ⭐ the repository