PumpSense provides a 280,000-post Telegram dataset with 2,246 labeled pumps and demonstrates BGE-M3 detection at F1 0.83 with 50ms latency plus LLM-based target extraction at 0.91 accuracy, outperforming rule-based methods.
Lld: A low latency detection solution to thwart cryptocurrency pump & dumps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PumpSense: Real-Time Detection and Target Extraction of Crypto Pump-and-Dumps on Telegram
PumpSense provides a 280,000-post Telegram dataset with 2,246 labeled pumps and demonstrates BGE-M3 detection at F1 0.83 with 50ms latency plus LLM-based target extraction at 0.91 accuracy, outperforming rule-based methods.