بسم الله الرحمن الرحيم
٤٤٩٬٢٨٥ حديث · ٣٧٬٠٤٦ راوٍ · ٨٦ مصنفاً · كل إسناد مُقَيَّم
The World's Most Comprehensive Computationally Graded Hadith Corpus
449,285 hadith from 86 classical works (v3.4 deployed; v3.26 staged adds 8,241 records from 6 more works) — every chain of transmission parsed, every narrator identified, every grade derived from documented inputs.
Built in public · External review cycle & quality practice
The corpus layer for TheoAI™ — reasoned over by Eve-Theology™ F5/reasoner.
Provenance & Audit Practice, Published
The only AI hadith corpus that ships an authoritative _provenanceDisclosure block in the manifest with every record — AI-involvement scope, regression suite, NAQD adversarial framework, and the recurring external review cycle, all visible. Read the disclosure →
Chain Authentication
Every hadith's chain parsed into narrator positions, identified against 27,118 NRS entries, graded by weakest link.
Content Analysis
First-ever computational matn criticism. Quran contradictions, fabrication patterns, anachronistic vocabulary, prophetic linguistic baseline.
Cross-Collection Linking
52,938 bag-of-words clusters plus semantic clusters at thresholds 0.85–0.92 (v3.12 fresh-embedding rebuild) linking the same hadith across all 86 collections with attestation levels.
Universal Narrator Identity
27,118 unique Person IDs. Same narrator across 5,000 chains always resolves to one ID.
Transmission Network
889,913 directed edges mapping 1,400 years of who-learned-from-whom.
Grade Provenance
Every grade traces to a specific narrator tier, a Taqrib entry, and a documented grading rule.
Taqwiyah Independence
Supporting chains verified for genuine independence. T10+ narrators cannot be elevated.
Fabrication Detection
NAQD-3 fresh-embedding re-run (v3.12): 1,851 findings — 300 critical, 638 high. 6,822 known fabrications validated. v3.26 source-collection caps applied to 2,168 records in fabrication anthologies (Mawḍūʿāt, Tanzīh, Fawāʾid).