Directed citation graphs plus textual embeddings reach 0.84-0.85 AUC for top-P% impact classification while GPT-5.5/5.4 Nano prompts hit 0.87 but show no consistent gain from retrieved graph neighborhoods over target-only baselines.
We kept the same controlled configuration used in the previous comparison: directed and unweighted graphs, with five randomly selected neighbors in the context-augmented condition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Node2Vec to GPT-based GraphRAG: scientific impact prediction across graph and language models
Directed citation graphs plus textual embeddings reach 0.84-0.85 AUC for top-P% impact classification while GPT-5.5/5.4 Nano prompts hit 0.87 but show no consistent gain from retrieved graph neighborhoods over target-only baselines.