SciEmbed-CTX
Signal A+B on a 7M-pair subsample (3 epochs). Best ablation; the FULL model is this recipe scaled to the full pool.
A 149M-parameter ModernBERT-base scientific document embedder trained with citation-context sentences as the primary contrastive signal. Part of the SciEmbed release (paper under double-blind review; author info omitted).
Usage
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("anon-nlp/sciembed-ctx")
emb = model.encode(["citation-context supervision for scientific embeddings"],
normalize_embeddings=True)
- Context length: 512 tokens
- Pooling: mean · Output dim: 768 (Matryoshka-truncatable to 512/256/128)
- License: MIT
SciRepEval (4-category macro)
| Classif. | Regr. | Prox. | Search | Overall |
|---|---|---|---|---|
| 75.5 | 28.3 | 80.9 | 82.5 | 66.8 ± 0.02 |
Citation
See the repository README. Paper: SciEmbed: Citation-Context Supervision for Scientific Document Embeddings (under review).