Beyond Pairwise Comparisons: A Distributional Test of Distinctiveness for Machine-Generated Works in Intellectual Property Law

2026-01-26

AI Summary

Current intellectual property law relies on pairwise comparisons to assess the novelty and originality of works, which is ill-suited for evaluating the fundamental differences between the output distributions of generative models and human-created content. This work proposes a two-sample test based on Maximum Mean Discrepancy (MMD) in semantic embedding space, enabling unsupervised, efficient, and distribution-level discrimination between human- and machine-generated content without requiring task-specific training or access to private data. Using only 5–10 images or 7–20 text samples, the method demonstrates consistent efficacy across three domains: handwritten digits, patent abstracts, and AI-generated art. Notably, it reliably detects the distinctiveness of generative model outputs in semantic space—even when human evaluators achieve only 58% accuracy—revealing these models to function essentially as stochastic interpolators rather than mere replicators of training data.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Computer Vision: Diffusion Models for Vision

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

Key doctrines, including novelty (patent), originality (copyright), and distinctiveness (trademark), turn on a shared empirical question: whether a body of work is meaningfully distinct from a relevant reference class. Yet analyses typically operationalize this set-level inquiry using item-level evidence: pairwise comparisons among exemplars. That unit-of-analysis mismatch may be manageable for finite corpora of human-created works, where it can be bridged by ad hoc aggregations. But it becomes acute for machine-generated works, where the object of evaluation is not a fixed set of works but a generative process with an effectively unbounded output space. We propose a distributional alternative: a two-sample test based on maximum mean discrepancy computed on semantic embeddings to determine if two creative processes-whether human or machine-produce statistically distinguishable output distributions. The test requires no task-specific training-obviating the need for discovery of proprietary training data to characterize the generative process-and is sample-efficient, often detecting differences with as few as 5-10 images and 7-20 texts. We validate the framework across three domains: handwritten digits (controlled images), patent abstracts (text), and AI-generated art (real-world images). We reveal a perceptual paradox: even when human evaluators distinguish AI outputs from human-created art with only about 58% accuracy, our method detects distributional distinctiveness. Our results present evidence contrary to the view that generative models act as mere regurgitators of training data. Rather than producing outputs statistically indistinguishable from a human baseline-as simple regurgitation would predict-they produce outputs that are semantically human-like yet stochastically distinct, suggesting their dominant function is as a semantic interpolator within a learned latent space.

Problem

• machine-generated works
• distinctiveness
• distributional comparison
• intellectual property law
• generative models

Innovation

• distributional test
• maximum mean discrepancy
• semantic embeddings
• generative models
• distinctiveness