Claims

Search Type State Status Topic Model Order Counting Over

As of snapshot 27745 under ledger-default@0.3.0.

Claim	Type	Assessment	Score	Review checks	References
Under combined semantics-preserving lexical perturbations, CausalVul's F1 dropped 5.1%, compared with 12.1–22.3% for the baselines evaluated in the study.	COMPARATIVE	Supported	0.8808	1 of 4	88
Under project-level group-aware evaluation on the Devign vulnerability-detection benchmark, CausalVul achieved 76.4% F1, 18.0 points above its fine-tuned CodeBERT backbone and 4.8 points above the UniXcoder baseline.	QUANTITATIVE	Leans supported	0.7029	1 of 4	113