datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
bitcoder-v2-eval
BitCoder-v2 Evaluation Dataset
Synthetic evaluation dataset accompanying the paper
"Routing Ceilings Are Domain-Independent: Structural Prior Injection
in Code Security Vulnerability Detection"
(arXiv:2607.14628).
Dataset Description
70 held-out evaluation pairs (140 records) across three vulnerability
categories, generated with DeepSeek-V4-Pro (temperature=0.8) via
Together AI.
Category
CWE
Type
Eval pairs
N+1 Query Pattern
--
Semantic
30… See the full description on the dataset page: https://huggingface.co/datasets/bytepro-ai/bitcoder-v2-eval.vector-sft2vector-9-14-sft2
