Convergence to the Truth

2024-10-15

arXiv.org

AI Summary

This paper addresses the normative evaluation of inference methods in philosophy of science by proposing and systematically developing “convergentism”—an epistemological tradition that evaluates inference methods primarily by their capacity to asymptotically approach truth across possible scenarios. Methodologically, it integrates Charles Sanders Peirce’s philosophical foundations, formal epistemic modeling, statistical consistency theory, and convergence analysis from machine learning to construct the first interdisciplinary framework for assessing truth-directedness. The framework is rigorously compared with three dominant paradigms—explanatory realism, instrumentalism, and Bayesianism—to clarify its logical foundations and domain of applicability. The study advances convergentism theoretically while delivering actionable criteria for AI interpretability assessment, model selection, and normative scientific reasoning—thereby bridging formal epistemology with contemporary computational practice.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Philosophy and Ethics of AI: AI & Epistemology

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

This article reviews and develops an epistemological tradition in the philosophy of science, known as convergentism, which holds that inference methods should be assessed based on their ability to converge to the truth across a range of possible scenarios. Emphasis is placed on its historical origins in the work of C. S. Peirce and its recent developments in formal epistemology and data science (including statistics and machine learning). Comparisons are made with three other traditions: (1) explanationism, which holds that theory choice should be guided by a theory's overall balance of explanatory virtues, such as simplicity and fit with data; (2) instrumentalism, which maintains that scientific inference should be driven by the goal of obtaining useful models rather than true theories; and (3) Bayesianism, which shifts the focus from all-or-nothing beliefs to degrees of belief.

Problem

• Assessing inference methods' truth convergence
• Exploring convergentism's origins and developments
• Comparing convergentism with other epistemological traditions

Innovation

• Convergentism assesses truth convergence
• Integrates Peirce's epistemology with data science
• Compares with explanationism, instrumentalism, Bayesianism