Empirica Dataset: Epistemic Self-Assessment for AI Systems

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: David Samuel Laurence Van Assche, Philipp Schwinger
DOI: 10.5281/zenodo.18237262
Cited by: 0

Abstract

Dataset (1,190,265 evidence observations from 792 AI sessions) and Brier Score companion guide for the Empirica epistemic measurement framework. Version 2.1.0 adds the mathematical formalization connecting Empirica to strictly proper scoring rules — covering the objective function, calibration/resolution decomposition, Bayesian updating, and earned agency as a function of Brier performance.

Fields of Study & Subjects

Ethics and Social Impacts of AI Epistemology Ethics and Metaphysics Artificial Intelligence Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
13 January 2026
Language
EN
Document type
Dataset