Al-Muhaddith Al-Raqami: Hybrid AI-Sanad Epistemology for Hadith Validation

The authenticity of hadith in the digital era is increasingly challenged by massive religious disinformation that outpaces conventional manual sanad criticism. This study aims to formulate a hybrid epistemological framework, Al-Muhaddith Al-Raqami, integrating classical naqd al-sanad methodology with Artificial Intelligence through an AI-Sanad model. Employing a qualitative library research design based on a Systematic Literature Review (2018–2025), this research analyzes classical ‘ulum al-hadith sources alongside contemporary computational studies in Natural Language Processing and Machine Learning. The findings demonstrate that the core principles of sanad evaluationittisal, ‘adalah, dhabt, syudzudz, and ‘illah can be translated into computational parameters through three interconnected stages: narrator extraction using Named Entity Recognition, sanad network modeling via Knowledge Graph, and automated hadith classification using machine learning algorithms. This integration establishes a structured AI-Sanad architecture that preserves methodological rigor while enabling scalable and data-driven validation. The model positions AI as an epistemic assistant rather than a substitute for scholarly authority, thereby inaugurating a new direction in computational hadith studies. The framework offers both theoretical advancement in digital Islamic epistemology and practical implications for strengthening critical religious literacy against disinformation.