Downloads · 30 days
0
Procedural-Reranker-Synthetic-v3-HardNegatives
dv4aby/Procedural-Reranker-Synthetic-v3-HardNegatives
Procedural-Reranker-Synthetic-v3-HardNegatives is a machine learning model from dv4aby. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is the Procedural Reranker v3 variant from the ablation study for the Structural Encoder V2.
Access
Public
Updated Dec 27, 2025
Repo size
708 B
Likes
0
Public
Repo makeup
Click a slice to open those files.
.py11.3 KB · 79%
At a glance
- Access
- Public
- Created
- Dec 27, 2025
- Updated
- Dec 27, 2025
- SHA
- 18bf7fdb
Model card
From the Hugging Face model README
Procedural Reranker v3 - Procedural Code Search
This is the Procedural Reranker v3 variant from the ablation study for the Structural Encoder V2.
Model Details
- Variant: reranker
- Dataset: POJ-104
- Architecture:
only_graph: Pure Structural Encoder (R-GNN only)concat: GraphCodeBERT + R-GNN (Concatenation Fusion)only_graph: Pure Structural Encoder (R-GNN only)concat: GraphCodeBERT + R-GNN (Concatenation Fusion)v2: GraphCodeBERT + R-GNN (Gated Fusion)reranker: Stage B Procedural Similarity Reranker (Logistic Regression)
Usage
This model requires the custom code structural_encoder_ablation.py and structural_encoder_v2.py.
- Created
- Dec 27, 2025
- Updated
- Dec 27, 2025