Skip to content
zk-Fair Docs
Search
Ctrl
K
Cancel
Select theme
Dark
Light
Auto
Getting Started
Introduction
Quick Start
Installation
Your First Model
Core Concepts
Architecture Overview
The Three Phases
IT-MAC Protocol
Zero-Knowledge Proofs
Fairness Metrics
Phase 1 - Certification
Overview
Training Your Model
Computing Commitments
Generating Proofs
On-Chain Registration
IT-MAC Key Setup
Phase 2 - Serving
Overview
Provider Setup
Query Authentication
Batch Commitments
Client Integration
Phase 3 - Auditing
Overview
Becoming an Auditor
Audit Triggers
Sampling Queries
Generating Proofs
Submitting Results
Smart Contracts
Model Registry
Auditor Pool
Query Batching
Proof Verification
Contract Events
ZK Circuits
Circuit 1: Training
Circuit 2: Fairness Audit
Input/Output Reference
Circuit Optimization
Testing Circuits
SDK Reference
CommitAPI
ProofAPI
ContractClient
InferenceClient
QueriesAPI
IT-MAC Library
ProviderITMAC
ClientITMAC
AuditorITMAC
ITMACSetup
ThresholdScheme
CLI Reference
model:commit
model:register
proof:training
proof:audit
client:query
auditor:register
Provider Guide
Setting Up Server
Loading Models
Event Listeners
Deployment Options
Monitoring & Logs
Client Guide
Querying Models
Storing Proofs
Verifying Commitments
Challenging Audits
Auditor Guide
Registration Process
Key Management
Running Audits
Earning Rewards
Reputation System
Examples
Adult Income Model
Credit Scoring Model
Loan Approval Model
Custom Model Integration
Advanced Topics
Threshold Cryptography
Merkle Tree Construction
VRF-based Sampling
Gas Optimization
Privacy Considerations
Deployment
Local Development
Testnet Deployment
Mainnet Deployment
Docker Setup
Railway/Fly.io
Troubleshooting
Common Errors
Debugging Tips
Performance Issues
FAQ
Research
OATH Paper Summary
Related Work
Future Directions
Academic Resources
Contributing
Development Setup
Code Style Guide
Pull Request Process
Testing Requirements
Appendix
Glossary
API Reference Tables
Gas Cost Tables
Benchmark Results
Select theme
Dark
Light
Auto
Training Your Model
Placeholder: Best practices for training models suitable for zk-Fair.