DIT: Dimension Reduction View on Optimal NFT Rarity Meters

2025-08-18

AI Summary

This paper addresses the core challenges of interpretability and cross-collection comparability in NFT rarity quantification. Methodologically, it proposes a novel rarity assessment framework grounded in dimensionality reduction, featuring a non-metric weighted multidimensional scaling (WMDS) optimization model and introducing *Dissimilarity in Trades* (DIT)—an unsupervised, data-driven rarity metric derived solely from on-chain transaction patterns. To ensure fair evaluation, the authors construct ROAR, a standardized benchmark comprising diverse NFT collections and evaluation protocols, enabling systematic comparison against state-of-the-art methods. Experiments demonstrate that DIT achieves statistically significant improvements over existing approaches on ROAR, while requiring no access to collection-level metadata—thereby exhibiting strong robustness and generalization. This work is the first to systematically apply dimensionality reduction principles to NFT rarity modeling, validating its superiority in low-explainability regimes and establishing a new paradigm for decentralized digital asset valuation.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Non-fungible tokens (NFTs) have become a significant digital asset class, each uniquely representing virtual entities such as artworks. These tokens are stored in collections within smart contracts and are actively traded across platforms on Ethereum, Bitcoin, and Solana blockchains. The value of NFTs is closely tied to their distinctive characteristics that define rarity, leading to a growing interest in quantifying rarity within both industry and academia. While there are existing rarity meters for assessing NFT rarity, comparing them can be challenging without direct access to the underlying collection data. The Rating over all Rarities (ROAR) benchmark addresses this challenge by providing a standardized framework for evaluating NFT rarity. This paper explores a dimension reduction approach to rarity design, introducing new performance measures and meters, and evaluates them using the ROAR benchmark. Our contributions to the rarity meter design issue include developing an optimal rarity meter design using non-metric weighted multidimensional scaling, introducing Dissimilarity in Trades (DIT) as a performance measure inspired by dimension reduction techniques, and unveiling the non-interpretable rarity meter DIT, which demonstrates superior performance compared to existing methods.

Problem

• Develop optimal NFT rarity meters using dimension reduction
• Introduce new performance measures for NFT rarity assessment
• Evaluate rarity meters with standardized ROAR benchmark

Innovation

• Optimal rarity meter using multidimensional scaling
• DIT measure inspired by dimension reduction
• Non-interpretable DIT meter outperforms existing methods