From Big Data to Valued Data: A Dataset Value Taxonomy for AI-Native Empirical Research

Abstract

Artificial intelligence is rapidly commoditizing many stages of empirical research, including code generation, statistical analysis, visualization, and manuscript drafting, yet its gains accrue unevenly across disciplines. As the marginal cost of these downstream tasks falls, the decisive bottleneck shifts to the data itself. The era of training and testing neural networks with ever-larger datasets is giving way to one in which the value of the data matters more than its volume. Building on but significantly revising earlier “Big Data” taxonomies, we introduce a Dataset Value Taxonomy (DVT) that reassesses the epistemic importance of datasets in an age where AI is commoditizing analytical labor. We argue that humans, as physically embodied agents, retain a comparative advantage in acquiring and curating observations from the world; partnered with AI, they can channel this advantage into higher-impact scholarship. To guide funders, evaluators, and researchers, we introduce a three-construct taxonomy: Temporal Investment, Scale, and Accessibility, each decomposed into measurable dimensions with ordinal class labels. We further operationalize these constructs through a calibrated scoring scheme that disciplines can adapt to field-specific conventions, enabling cross-field comparability while respecting contextual nuance. By quantifying how temporal investment, observational breadth, and access barriers jointly determine dataset salience, the framework helps allocate resources toward datasets that are most likely to advance knowledge. Ultimately, our taxonomy positions dataset creation as the new core site of human and AI cooperation and provides an actionable roadmap for recognizing, funding, and stewarding high-value data assets across the empirical sciences.