Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CoinCLIP: A Multimodal Framework for Assessing Viability in Web3 Memecoins

Hou-Wan Long, Hongyang Li, Wei Cai

TL;DR

This work tackles the problem of distinguishing viable memecoins from a flood of low-quality tokens on Web3 platforms like Pump.fun. It introduces CoinVibe, a multimodal dataset combining textual descriptions, logos, and community signals to assess memecoin viability, and CoinCLIP, a CLIP-based classifier augmented with lightweight modality-specific adapters and community data. Through extensive experiments, CoinCLIP outperforms unimodal and other multimodal baselines in accuracy, AUROC, and F1, with ablation confirming the value of projection layers, adapters, and community information. The results offer a data-driven framework for investors and developers to filter memecoins and provide insights into the multimodal factors contributing to long-term success in the memecoin ecosystem.

Abstract

The rapid growth of memecoins within the Web3 ecosystem, driven by platforms like Pump.fun, has made it easier for anyone to create tokens. However, this democratization has also led to an explosion of low-quality or bot-generated projects, often motivated by short-term financial gain. This overwhelming influx of speculative tokens creates a challenge in distinguishing viable memecoins from those that are unlikely to succeed. To address this issue, we introduce CoinVibe, a comprehensive multimodal dataset designed to evaluate the viability of memecoins. CoinVibe integrates textual descriptions, visual content (logos), and community data (user comments, timestamps, and number of likes) to provide a holistic view of a memecoin's potential. In addition, we present CoinCLIP, a novel framework that leverages the Contrastive Language-Image Pre-Training (CLIP) model, augmented with lightweight modules and community data integration, to improve classification accuracy. By combining visual and textual representations with community insights, CoinCLIP provides a robust, data-driven approach to filter out low-quality or bot-driven projects. This research aims to help creators and investors identify high-potential memecoins, while also offering valuable insights into the factors that contribute to their long-term success. The code and dataset are publicly available at https://github.com/hwlongCUHK/CoinCLIP.git.

CoinCLIP: A Multimodal Framework for Assessing Viability in Web3 Memecoins

TL;DR

This work tackles the problem of distinguishing viable memecoins from a flood of low-quality tokens on Web3 platforms like Pump.fun. It introduces CoinVibe, a multimodal dataset combining textual descriptions, logos, and community signals to assess memecoin viability, and CoinCLIP, a CLIP-based classifier augmented with lightweight modality-specific adapters and community data. Through extensive experiments, CoinCLIP outperforms unimodal and other multimodal baselines in accuracy, AUROC, and F1, with ablation confirming the value of projection layers, adapters, and community information. The results offer a data-driven framework for investors and developers to filter memecoins and provide insights into the multimodal factors contributing to long-term success in the memecoin ecosystem.

Abstract

The rapid growth of memecoins within the Web3 ecosystem, driven by platforms like Pump.fun, has made it easier for anyone to create tokens. However, this democratization has also led to an explosion of low-quality or bot-generated projects, often motivated by short-term financial gain. This overwhelming influx of speculative tokens creates a challenge in distinguishing viable memecoins from those that are unlikely to succeed. To address this issue, we introduce CoinVibe, a comprehensive multimodal dataset designed to evaluate the viability of memecoins. CoinVibe integrates textual descriptions, visual content (logos), and community data (user comments, timestamps, and number of likes) to provide a holistic view of a memecoin's potential. In addition, we present CoinCLIP, a novel framework that leverages the Contrastive Language-Image Pre-Training (CLIP) model, augmented with lightweight modules and community data integration, to improve classification accuracy. By combining visual and textual representations with community insights, CoinCLIP provides a robust, data-driven approach to filter out low-quality or bot-driven projects. This research aims to help creators and investors identify high-potential memecoins, while also offering valuable insights into the factors that contribute to their long-term success. The code and dataset are publicly available at https://github.com/hwlongCUHK/CoinCLIP.git.

Paper Structure

This paper contains 12 sections, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Pump.fun Memecoins and Related Work
  3. Dataset Description
  4. Data Acquisition
  5. Data Cleansing
  6. Data Annotation
  7. Methodology
  8. Experiment
  9. Experiment Setting
  10. Experiment Result
  11. Ablation Study
  12. Conclusion

Figures (1)

  • Figure 1: An overview of our proposed framework, CoinCLIP. We use frozen CLIP image and text encoders to create representations for each image-text pair. These representations are passed through linear layers to disentangle the modalities in CLIP’s shared embedding space. We implement Feature Adapters with residual connections for each modality to prevent overfitting. Community data is integrated to enhance the performance.