Paper: arXiv 2602.14860

Authors: Giulio Marino, Manuel Naviglio, Francesco Tarantelli, Fabrizio Lillo

Abstract

We study the dynamics of token launched on Pump.fun, a Solana-based launchpad platform, to identify the determinants of the token success. Pump.fun employs a bonding curve mechanism to bootstrap initial liquidity possibly leading to graduation to the on-chain market, which can be seen as a token success. We build predictive models of the probability of graduation conditional on the current amount of Solana locked in the bonding curve and a set of explanatory variables that capture structural and behavioral aspects of the launch process. Conditioning the graduation probability on these variables significantly improves its predictive power, providing insights into early-stage market behavior, speculative and manipulative dynamics, and the informational efficiency of bonding-curve-based token launches.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper provides a strong empirical analysis of token graduation dynamics on Pump.fun using microstructural and behavioral on-chain data. While the mathematical formulations are relatively lightweight (focused on conditional probabilities and bonding curve mechanics), the empirical setup and predictive insights are novel and well-executed.

Research Flowchart

  flowchart TD
    A[Research Goal: Predict token graduation success on Pump.fun] --> B[Data Collection: Solana bonding curve & token launch metrics]
    B --> C[Feature Engineering: Extract structural & behavioral variables]
    C --> D[Predictive Modeling: Model graduation probability conditioned on SOL locked]
    D --> E[Outcome: Enhanced predictive power & insights on speculative market dynamics]

Cited References (28)

  1. Uniswap v2 Core (2020)
  2. Improved Price Oracles: Constant Function Market Makers (2020)
  3. Pump.fun: Solana Token Launchpad (2024)
  4. Price manipulation schemes of new crypto-tokens in decentralized exchanges (2025) — link
  5. Quantifying Blockchain Extractable Value: How dark is the forest? (2021) — link
  6. The Art of The Scam: Demystifying Honeypots in Ethereum Smart Contracts (2019) — link
  7. SoK: Comprehensive Analysis of Rug Pull Causes, Datasets, and Detection Tools in DeFi (2024) — link
  8. Flash Boys 2.0: Front-Running, Transaction Reordering, and Consensus Instability in Decentralized Exchanges (2020) — link
and 20 more
  1. Automated Agents in Decentralized Exchanges: Evidence from Uniswap (2022)
  2. An Analysis of Constant Function Market Makers (2020) — link
  3. Formal Foundations of Automated Market Makers (2020)
  4. Decentralized Exchanges: The Good, the Bad, and the Ugly (2021)
  5. The Adoption of Decentralized Exchanges (2022)
  6. Automated Market Making and Arbitrage (2022)
  7. LLD: A Low Latency Detection Solution to Thwart Cryptocurrency Pump & Dumps (2023) — link
  8. Detecting stock market manipulation using supervised learning algorithms (2014) — link
  9. An examination of the cryptocurrency pump-and-dump ecosystem (2021) — link
  10. Exact Results for Shewhart Control Charts with Supplementary Runs Rules (1987) — link
  11. To the moon: defining and detecting cryptocurrency pump-and-dumps (2018) — link
  12. Improving Cryptocurrency Pump-and-Dump Detection through Ensemble-Based Models and Synthetic Oversampling Techniques — → 2510.00836
  13. On the Risk Spillover from Bitcoin to Altcoins: The Fear of Missing Out and Pump-and-Dump Scheme Effects (2023) — link
  14. Detecting Pump-and-Dumps with Crypto-Assets: Dealing with Imbalanced Datasets and Insiders’ Anticipated Purchases (2023) — link
  15. Beauty Contests and Iterated Expectations in Asset Markets (2006) — link
  16. The General Theory of Employment, Interest and Money (1936)
  17. Social Value of Public Information (2002) — link
  18. Alternatives to the Median Absolute Deviation (1993) — link
  19. Pump.fun Debuts New Investment Arm Pump Fund — link
  20. 0 (0)

1 of 28 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.