Reject negative PyTorch one-hot class counts

[FlorianPfaff]

Summary

• reject negative num_classes values in the PyTorch one_hot compatibility layer
• cover both Python integers and scalar PyTorch tensors
• verify the behavior through the raw PyTorch backend and the public PyTorch backend facade

Root cause

PyTorch reserves num_classes=-1 as a sentinel that infers the class count from the labels. PyRecEst exposes num_classes as an explicit dimension, and its NumPy/JAX implementations reject negative dimensions. Passing -1 therefore silently produced a valid one-hot matrix only on the PyTorch backend instead of rejecting invalid input.

Impact

Invalid negative class counts now fail consistently instead of changing meaning depending on the selected backend.

Validation

• reproduced the pre-fix behavior under both NumPy-active/raw-PyTorch and public PyTorch configurations
• exercised the patched compatibility hook locally for both configurations
• preserved scalar-label, batched-label, dtype, and device behavior

[github-actions]

✅MegaLinter analysis: Success

Descriptor	Linter	Files	Fixed	Errors	Warnings	Elapsed time
✅ COPYPASTE	jscpd	yes		no	no	24.05s
✅ JSON	prettier	7	0	0	0	1.19s
✅ JSON	v8r	7		0	0	4.37s
✅ MARKDOWN	markdownlint	68	0	0	0	2.0s
✅ MARKDOWN	markdown-table-formatter	68	0	0	0	0.54s
✅ PYTHON	black	1563	208	0	0	102.78s
✅ PYTHON	isort	1563	382	0	0	2.81s
✅ REPOSITORY	betterleaks	yes		no	no	2.41s
✅ REPOSITORY	checkov	yes		no	no	57.29s
✅ REPOSITORY	gitleaks	yes		no	no	15.61s
✅ REPOSITORY	git_diff	yes		no	no	0.29s
✅ REPOSITORY	secretlint	yes		no	no	76.97s
✅ REPOSITORY	syft	yes		no	no	5.31s
✅ REPOSITORY	trivy-sbom	yes		no	no	6.97s
✅ REPOSITORY	trufflehog	yes		no	no	33.17s
✅ YAML	prettier	11	0	0	0	0.74s
✅ YAML	v8r	11		0	0	11.36s
✅ YAML	yamllint	11		0	0	0.67s

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