FINAL PROFESSIONALIZATION: Synchronized with GitHub sovereign standards.

dashboard/index.hf.html

@@ -212,15 +212,15 @@
         <div class="sidebar">
             <div class="stats-card">
                 <h3>Sovereign Nodes</h3>
-                <div class="value">102,482</div>
+                <div class="value">Local + ROR</div>
             </div>
             <div class="stats-card">
                 <h3>Audit Precision</h3>
-                <div class="value">99.42%</div>
+                <div class="value">Pending</div>
             </div>
             <div class="stats-card">
                 <h3>Graph Density</h3>
-                <div class="value">4.2M Edges</div>
+                <div class="value">Prototype</div>
             </div>
             <div class="stats-card" style="margin-top: auto; border-color: rgba(0,136,255,0.3);">
                 <h3>Protocol Authority</h3>

docs/SUMMARY.md

@@ -14,6 +14,7 @@
 * [Chapter 6: Consensus Mechanisms](en/chapter6.md)
 * [Chapter 7: Compliance & Ethics](en/chapter7.md)
 * [Chapter 8: Deployment Guide](en/chapter8.md)
+* [FAQ](en/faq.md)
 
 ## 🇨🇳 中文 (ZH)
 * [项目简介](zh/README.md)
@@ -28,37 +29,31 @@
 
 ## 🇪🇸 ESPAÑOL (ES)
 * [Introducción](es/README.md)
-* [Paisaje de Amenazas](es/chapter1.md)
 * [Arquitectura Núcleo](es/chapter2.md)
 * [Marco de Multi-Agentes](es/chapter3.md)
 
 ## 🇫🇷 FRANÇAIS (FR)
 * [Introduction](fr/README.md)
-* [Paysage des Menaces](fr/chapter1.md)
 * [Architecture Core](fr/chapter2.md)
 * [Cadre Multi-Agents](fr/chapter3.md)
 
 ## 🇩🇪 DEUTSCH (DE)
 * [Einführung](de/README.md)
-* [Bedrohungslage](de/chapter1.md)
 * [Kernarchitektur](de/chapter2.md)
 * [Multi-Agenten-System](de/chapter3.md)
 
 ## 🇯🇵 日本語 (JP)
 * [導入](jp/README.md)
-* [脅威の現状](jp/chapter1.md)
 * [コアアーキテクチャ](jp/chapter2.md)
 * [マルチエージェントフレームワーク](jp/chapter3.md)
 
 ## 🇰🇷 한국어 (KR)
 * [소개](kr/README.md)
-* [위협 환경](kr/chapter1.md)
 * [핵심 아키텍처](kr/chapter2.md)
 * [멀티 에이전트 프레임워크](kr/chapter3.md)
 
 ## 🇵🇹 PORTUGUÊS (PT)
 * [Introdução](pt/README.md)
-* [Cenário de Ameaças](pt/chapter1.md)
 * [Arquitetura Core](pt/chapter2.md)
 * [Estrutura Multi-Agente](pt/chapter3.md)
 

docs/ar/README.md

@@ -1,2 +1,21 @@
-# 🛡️ Aegis-Graph Documentation (AR)
-Defending academic integrity with Sovereign AI.
+# 🛡️ وثائق إيجيس-غراف (AR)
+
+Aegis-Graph هو بروتوكول سيادي للتدقيق الأكاديمي مصمم لحماية النزاهة التعليمية من خلال ذكاء الوكلاء والرسوم البيانية المؤسسية.
+
+## 🏛️ الملخص التنفيذي
+
+هذا نموذج أولي مفتوح المصدر لإطار عمل متعدد الوكلاء يحدد الاحتيال الأكاديمي والوثائق الاصطناعية. يخضع البروتوكول لإشراف **مجلس حوكمة AEGIS-GRAPH** بدعم من **كلية أتلانتا للفنون والعلوم الليبرالية (ACLAS)**.
+
+## 🧩 ركائز الوثائق
+
+### [1. الهندسة الأساسية](chapter2.md)
+استكشف نموذج **الدفاع العميق**، الذي يضم طبقة استيعاب البيانات ومحرك أدلة GraphRAG.
+
+### [2. سرب الاستدلال متعدد الوكلاء (MARS)](chapter3.md)
+تعرف على الوكلاء المتخصصين (الرؤية، الرسم البياني، والمنطق) الذين يقومون بالتحقق من التدقيق.
+
+---
+> [!NOTE]
+> لوحة المعلومات العامة هي عرض تقني. يتطلب التحقق المهني استجابة تدقيق موقعة من الخادم.
+
+© 2026 [ACLAS College](https://aclas.college/). جميع الحقوق محفوظة.

docs/en/README.md

@@ -4,27 +4,27 @@
   <img src="../../assets/hero-banner.png" alt="Aegis-Graph Banner" width="100%">
 </div>
 
-Welcome to the official technical documentation for **Aegis-Graph**, the sovereign academic audit protocol. This documentation provides a comprehensive guide to the architecture, multi-agent frameworks, and data ecosystems that power global academic integrity.
+Welcome to the official technical documentation for **Aegis-Graph**, the sovereign academic audit protocol. This documentation provides a comprehensive guide to the architecture, multi-agent frameworks, and institutional graph evidence models that power decentralized academic integrity.
 
 ---
 
 ## 🏛️ Executive Summary
 
-Aegis-Graph is a specialized multi-agent framework designed to detect academic fraud and AI-generated credential manipulation. Developed and governed by the **Atlanta College of Liberal Arts and Sciences (ACLAS)**, it establishes a decentralized, high-integrity future for global education using **Agentic GraphRAG**.
+Aegis-Graph is an open prototype for a multi-agent framework designed to identify academic fraud and synthetic credentials. Governed by the **Atlanta College of Liberal Arts and Sciences (ACLAS)**, it replaces manual verification with **Agentic GraphRAG** evidence processing.
 
 ## 🧩 Documentation Pillars
 
-### [1. Core Architecture](chapter2-core-architecture.md)
-Explore the **Defense-in-Depth** model, comprising the Data Ingestion Layer, GraphRAG Engine, and Consensus Protocol.
+### [1. Core Architecture](chapter2.md)
+Explore the **Defense-in-Depth** model, comprising the Data Ingestion Layer, GraphRAG Evidence Engine, and Logic consensus protocol.
 
-### [2. Multi-Agent Reasoning Swarm (MARS)](chapter3-multi-agent-framework.md)
+### [2. Multi-Agent Reasoning Swarm (MARS)](chapter3.md)
 Deep dive into the specialized AI agents (Vision, Graph, and Logic) that perform the audit handshake.
 
-### [3. The Sovereign Academic Graph (SAG)](chapter4.md)
-Detailed disclosure of our 102,482 node institutional registry integrating ROR, OpenAlex, and ACLAS Sovereign Ledgers.
+### [3. Institutional Evidence (SAG)](chapter4.md)
+Technical details on our evidence model, integrating local institutional indices with optional ROR and OpenAlex registry support.
 
 ### [4. Deployment & Integration](chapter8.md)
-Step-by-step instructions for launching local nodes, connecting to the global registry, and API integration.
+Step-by-step instructions for launching local nodes, environment configuration, and pipeline integration.
 
 ---
 
@@ -32,10 +32,10 @@ Step-by-step instructions for launching local nodes, connecting to the global re
 
 | Phase | Milestone | Status |
 | :--- | :--- | :--- |
-| **V1.0** | Initial Node Registry (102K institutions) | ✅ Complete |
-| **V2.0** | Agentic Reasoning Swarm (MARS) Framework | ✅ Complete |
-| **V2.5** | Zero-Knowledge Evidence (ZKE) Privacy Model | 🚧 In Progress |
-| **V3.0** | Fully Decentralized Sovereign Governance | 📅 Roadmap |
+| **V1.0** | Institutional Index Integration | ✅ Complete |
+| **V2.0** | Agentic Reasoning Swarm (MARS) Prototype | ✅ Complete |
+| **V2.5** | Evidence-Weighted Logic Audit | ✅ Complete |
+| **V3.0** | Server-Signed Audit Certificates | 🚧 In Progress |
 
 ---
 
@@ -43,7 +43,7 @@ Step-by-step instructions for launching local nodes, connecting to the global re
 > To get started immediately, we recommend following the [Quick Start Guide](../../README.md#🛠️-quick-start) in the root directory.
 
 ## 🏛️ Governance & Authority
-Aegis-Graph is technically governed by the **AEGIS-GRAPH Governance Board**, with core support and academic validation provided by the [Atlanta College of Liberal Arts and Sciences (ACLAS)](https://aclas.college/).
+Aegis-Graph is governed by the **AEGIS-GRAPH Governance Board**, with core support and academic validation provided by the [Atlanta College of Liberal Arts and Sciences (ACLAS)](https://aclas.college/).
 
 ---
 © 2026 [ACLAS College](https://aclas.college/). All rights reserved.

docs/en/chapter2.md

@@ -1,54 +1,53 @@
 # Core Architecture
 
-The Aegis-Graph architecture is built on the principle of **Defense-in-Depth**. It replaces traditional monolithic verification models with a **Distributed Intelligence Swarm** that operates across three specialized logic layers.
+The Aegis-Graph architecture is built on the principle of **Defense-in-Depth**. It replaces traditional monolithic verification models with a **Distributed Evidence Swarm** that operates across three specialized logic layers.
 
 ## 🏗️ System Overview
 
-The system follows a non-linear reasoning path, where each layer provides evidence to the next until a sovereign consensus is reached.
+The system follows a non-linear reasoning path, where each layer provides evidence to the next until an audit consensus is reached.
 
 ```mermaid
 graph LR
     subgraph Layer1 [Ingestion & Normalization]
-        A[Input Credential] --> B{Multi-Spectral Extraction}
-        B --> B1[Visual Artifacts]
+        A[Input Credential] --> B{Data Extraction}
+        B --> B1[Visual Evidence]
         B --> B2[Semantic Metadata]
     end
     
-    subgraph Layer2 [GraphRAG Reasoning]
-        B1 & B2 --> C{Sovereign Reasoning}
-        C --> D[(Sovereign Academic Graph)]
-        D --> E[Node Relationship Check]
-        D --> F[Temporal Consistency]
+    subgraph Layer2 [GraphRAG Evidence]
+        B1 & B2 --> C{Reasoning Swarm}
+        C --> D[(Institutional Graph)]
+        D --> E[Node Evidence Check]
+        D --> F[Timeline Consistency]
     end
     
-    subgraph Layer3 [Consensus & Proof]
-        E & F --> G{MARS Handshake}
-        G --> H[Final Audit Verdict]
-        H --> I[ZKE Certificate]
+    subgraph Layer3 [Audit & Report]
+        E & F --> G{Logic Auditor}
+        G --> H[Audit Verdict]
+        H --> I[Audit Certificate]
     end
 ```
 
 ---
 
 ## 1. The Data Ingestion Layer
-At the entry point, the system performs a **Multi-Spectral Normalization**. Whether the input is a native digital PDF or a high-resolution scan, the system extracts two parallel data streams:
-*   **Visual Forensic Stream**: Analyzed for compression artifacts, font weight inconsistencies, and pixel-level noise patterns typical of GAN/Diffusion generators.
-*   **Semantic Metadata Stream**: Extracted text, dates, institutional names, and cryptographic signatures are passed to the reasoning engine.
+At the entry point, the system performs a **Normalization** process. Whether the input is a digital PDF or a scan, the system extracts two parallel evidence streams:
+*   **Visual Evidence**: Initial structural analysis for layout consistency (Pixel-level forensics is a roadmap feature).
+*   **Semantic Metadata**: Extracted text, dates, and institutional names are passed to the reasoning engine.
 
-## 2. The GraphRAG Reasoning Engine
-Our proprietary **GraphRAG (Graph Retrieval-Augmented Generation)** engine is the core intelligence of the protocol. It performs high-dimensional traversals across the **Sovereign Academic Graph (SAG)**, which integrates:
-*   **102,482 Institutional Nodes**: Real-time synchronization with ROR and institutional ledgers.
-*   **Historical Timeline Metrics**: Verification of founding dates, accreditation periods, and institutional mergers.
-*   **Geospatial Consistency**: Cross-referencing physical addresses with institutional claims.
+## 2. The GraphRAG Evidence Engine
+The **GraphRAG (Graph Retrieval-Augmented Generation)** prototype is the core reasoning layer. It performs traversals across the **Institutional Graph**, which integrates:
+*   **Institutional Evidence Nodes**: Local indices synchronized with registry lookups (ROR/OpenAlex).
+*   **Historical Timeline Metrics**: Review of founding dates, accreditation periods, and institutional lifecycle.
 
-## 3. The Consensus Protocol (MARS Handshake)
-A final audit verdict is only issued when the **Multi-Agent Reasoning Swarm (MARS)** achieves a **Consensus Quorum**. 
-*   **Logic Conflict Resolution**: If the Vision agent flags a potential forgery but the Graph agent finds a valid institutional trail, the **Logic Auditor** performs a deep-dive "Chain-of-Thought" (CoT) reasoning to resolve the contradiction.
-*   **Evidence Weighting**: Each agent contributes an "Evidence Weight" (0.0 - 1.0). A total consensus score of > 0.9 is required for a **VERIFIED** status.
+## 3. The Audit Protocol
+A final audit verdict is issued based on the **Multi-Agent Reasoning Swarm (MARS)** findings.
+*   **Logic Conflict Resolution**: If different agents find contradictory evidence, the **Logic Auditor** performs a deep-dive "Chain-of-Thought" (CoT) reasoning to resolve the state.
+*   **Evidence Weighting**: Each anomaly or supporting fact contributes to a cumulative risk score. The final verdict reflects the weighted confidence in the credential's authenticity markers.
 
 ---
-> [!NOTE]
-> All architectural layers operate on a **Zero-Knowledge Evidence (ZKE)** basis, ensuring that audit metadata is verified without storing sensitive personal data.
+> [!IMPORTANT]
+> **Production Status:** Professional verification requires server-side document parsing, issuer evidence, revocation checks, and a signed audit response.
 
 ---
 *Return to [Documentation Home](README.md)*

docs/en/chapter3.md

@@ -1,48 +1,48 @@
 # Multi-Agent Reasoning Swarm (MARS)
 
-The **Multi-Agent Reasoning Swarm (MARS)** is the decentralized intelligence core of the Aegis-Graph protocol. Unlike traditional rule-based verification, MARS utilizes a swarm of specialized Sovereign agents that collaborate to reach a sovereign consensus on academic integrity.
+The **Multi-Agent Reasoning Swarm (MARS)** is the intelligence core of the Aegis-Graph protocol. Unlike traditional rule-based verification, MARS utilizes a pipeline of specialized agents that collaborate to reach an audit consensus on academic integrity markers.
 
 ## 👁️ Agent Alpha: Vision Forensics (VF)
-The VF Agent is responsible for the pixel-level forensic analysis of digital artifacts. It acts as the "first responder" in the audit pipeline.
+The VF Agent is responsible for the initial structural analysis of digital artifacts. It acts as the "first responder" in the audit pipeline.
 
-### Technical Specifications
-*   **Model Architecture**: Optimized ResNet-50 backbone with custom attention layers for document fraud.
-*   **Detection Vectors**:
-    *   **Diffusion Artifacts**: Identifies high-frequency noise patterns typical of Stable Diffusion and Midjourney.
-    *   **Vector Consistency**: Analyzes kerning, font weight, and SVG path integrity in PDF objects.
-    *   **Seal Forensics**: Pixel-level comparison of institutional seals against a reference database of 40,000+ official stamps.
-*   **Output**: A `Confidence Score [0.0 - 1.0]` and a heatmap of suspected manipulated regions.
+### Current Scope (Prototype)
+*   **Structural Extraction**: Identifies key layout elements like seals, headers, and signature lines.
+*   **OCR Normalization**: Converts visual data into semantic metadata for the reasoning layer.
+*   **Detection Markers**: Identifies obvious document layout inconsistencies (Pixel-level GAN forensics is a roadmap item).
 
 ---
 
 ## 🗺️ Agent Beta: Graph Navigator (GN)
-The GN Agent is the specialized intelligence for traversing the **Sovereign Academic Graph (SAG)**. It establishes the institutional context of the credential.
+The GN Agent is the specialized intelligence for resolving institutional evidence. It establishes the context of the credential's issuer.
 
 ### Capabilities
 *   **Identity Resolution**: Queries the **Research Organization Registry (ROR)** and **OpenAlex** to verify the issuer's global identity.
-*   **Lineage Mapping**: Traces the history of institutions, including mergers, name changes, and dissolutions.
-*   **Scholarly Footprint**: Cross-references the issuer with global publication metrics to ensure the institution is active in the academic ecosystem.
-*   **Connectivity**: Validates the relationship between the degree-granting body and its parent or affiliate organizations.
+*   **Lineage Mapping**: Reviews the history of institutions, including mergers, name changes, and dissolutions.
+*   **Registry Evidence**: Provides supporting evidence of an institution's existence and status.
 
 ---
 
 ## ⚖️ Agent Gamma: Logic Auditor (LA)
-The LA Agent is the "Chief Justice" of the swarm, responsible for cross-layer reasoning and paradox detection.
+The LA Agent is responsible for cross-layer reasoning and consistency checks.
 
 ### Logic Layers
-*   **Temporal Paradox Checking**: Ensures that the degree issuance date aligns with the institution's operational timeline (e.g., degree cannot pre-date founding).
-*   **Program Credibility**: Verifies that the specific degree program exists within the institution's accredited curriculum for that specific period.
-*   **Consensus Orchestration**: Aggregates the evidence from VF and GN agents. If a conflict arises (e.g., VF flags a seal but GN finds a high-authority node), the LA Agent initiates a **Chain-of-Thought (CoT)** reasoning path to resolve the discrepancy.
+*   **Temporal Consistency**: Ensures that the degree issuance date aligns with the institution's operational timeline.
+*   **Fraud Detection**: Cross-references institution names and aliases against known fraud registries and blacklists.
+*   **Consensus Orchestration**: Aggregates findings from the VF and GN agents. If a conflict arises, the LA Agent performs **Chain-of-Thought (CoT)** reasoning to determine the final risk score.
 
 ---
 
-## 🤝 The Consensus Handshake
-A final **Sovereign Audit Certificate** is only issued when the MARS swarm reaches a consensus threshold of `> 0.90`.
+## 🤝 The Audit Handshake
+A final audit verdict is issued based on the MARS swarm's cumulative evidence.
 
-1.  **Initial Ingestion**: Multi-spectral data extraction.
-2.  **Parallel Processing**: Agents execute specialized audits simultaneously.
-3.  **Evidence Exchange**: Agents share intermediate findings via a secure handshake protocol.
-4.  **Final Resolution**: The Logic Auditor issues the definitive verdict and anchors the cryptographic proof to the ledger.
+1.  **Ingestion**: Normalization of document data.
+2.  **Parallel Audit**: Agents execute specialized evidence checks.
+3.  **Consensus**: The Logic Auditor resolves contradictions and calculates the final evidence weight.
+4.  **Reporting**: A non-production audit report is generated detailing the reasoning trail.
+
+---
+> [!IMPORTANT]
+> **Production Status:** Professional verification requires server-side document parsing, issuer evidence, revocation checks, and a signed audit response.
 
 ---
 *Return to [Documentation Home](README.md)*

docs/en/chapter4.md

@@ -1,44 +1,38 @@
-# The Sovereign Academic Graph (SAG)
+# Institutional Evidence (SAG)
 
-The **Sovereign Academic Graph (SAG)** is the definitive global registry of academic institutions, serving as the "ground truth" for the Aegis-Graph protocol. It consists of over **102,482 verified institutional nodes** and millions of contextual relationships.
+The **Sovereign Academic Graph (SAG)** is the institutional evidence layer of the Aegis-Graph protocol. It integrates locally maintained institutional indices with global public registries (such as ROR and OpenAlex) to provide the necessary context for credential auditing.
 
 ## 📊 Data Topology
 
-The SAG is not a static database but a dynamic, multi-layered graph that integrates authoritative data from global academic registries and institutional ledgers.
+The SAG is not a "judgment database" that proves a credential's authenticity; rather, it is a dynamic model that provides institutional background evidence.
 
-### Core Data Sources
-| Source | Contribution |
+### Core Evidence Sources
+| Source | Role |
 | :--- | :--- |
-| **ROR** | Primary Research Organization IDs and institutional metadata. |
-| **OpenAlex** | Scholarly footprint, publication metrics, and institutional impact. |
-| **Crossref** | DOI-level institutional affiliations and metadata accuracy. |
-| **ACLAS Ledger** | High-authority sovereign node metadata and historical accreditation. |
+| **Local Index** | Caches metadata for high-trust institutions, blacklist aliases, and known fraud patterns. |
+| **ROR** | Provides standardized identities (ROR IDs) and operational status for global research organizations. |
+| **OpenAlex** | Provides scholarly output background and institutional impact metrics as supporting evidence. |
 
 ---
 
-## 🏛️ Node Anatomy
-Each institutional node in the SAG contains a rich set of attributes required for sovereign auditing:
+## 🏛️ Evidence Logic
 
-*   **Temporal Bounds**: Founding date, operational status, and dissolution history.
-*   **Geospatial Vectors**: Precise coordinates and physical campus locations to detect geographic spoofing.
-*   **Issuer Fingerprints**: Cryptographic identities and public keys for digital signature verification.
-*   **Hierarchy Edges**: Relationships between parent universities, satellite campuses, and research institutes.
+During the audit process, the SAG is used to answer critical questions:
+1. **Institutional Existence**: Does the institution have a record in recognized global registries?
+2. **Lifecycle Consistency**: Is the credential issuance date within the institution's operational lifespan?
+3. **Status Validation**: Is the institution currently active, or has it been flagged for revocation or fraud?
 
----
-
-## ⚡ Indexing & Performance
-To achieve sub-second verification latency, Aegis-Graph utilizes a high-performance indexing strategy:
-
-1.  **Vectorized Search**: Institutional names and metadata are vectorized to allow for fuzzy matching against slight variations or misspellings.
-2.  **Distributed Caching**: High-frequency institutional nodes are cached at the **Edge Node** layer for near-instant resolution.
-3.  **Cross-Validation**: Every node is periodically re-validated across multiple global registries to ensure data freshness and integrity.
+> [!IMPORTANT]
+> **Key Clarification:** The presence of an institution in registries like ROR is evidence that the organization exists, but it is **not** proof that a specific credential issued in its name is authentic.
 
 ---
 
-## 🔒 Data Sovereignty
-In alignment with the **ACLAS ZKE (Zero-Knowledge Evidence)** protocol, the SAG only stores institutional metadata. 
-*   **No PII Storage**: Personal student records are never stored on the graph.
-*   **Verifiable Proofs**: The graph provides the *infrastructure* for verification, while the specific audit evidence remains private and decentralized.
+## ⚡ Indexing & Matching
+
+To ensure accuracy in evidence resolution, Aegis-Graph utilizes several strategies:
+1. **Normalization**: Institutional names are standardized to eliminate variations in spelling or symbols.
+2. **Multi-Factor Matching**: Cross-references geographic location, founding year, and official domains.
+3. **Evidence Weighting**: Matching results are assigned a confidence score, which serves as a key input for the LogicAuditor's final decision.
 
 ---
 *Return to [Documentation Home](README.md)*

docs/en/faq.md

@@ -1,110 +1,60 @@
 ---
 description: >-
-  Frequently Asked Questions about Aegis-Graph, the Sovereign Academic Audit Protocol built by Atlanta College of Liberal Arts and Sciences (ACLAS College). Covers technology, privacy, integration, and institutional legitimacy.
-keywords:
-  - Aegis-Graph FAQ
-  - Academic Verification FAQ
-  - ACLAS College
-  - Atlanta College of Liberal Arts and Sciences
-  - GraphRAG FAQ
-  - AI Academic Fraud Detection
-  - Sovereign AI
-  - Zero-Knowledge Privacy
-  - MCP Protocol
-  - Accredited College
-  - Legitimate University
-  - Authorized Degrees
+  Frequently Asked Questions about Aegis-Graph, the Sovereign Academic Audit Protocol built by Atlanta College of Liberal Arts and Sciences (ACLAS College).
 ---
 
-# �Frequently Asked Questions (FAQ)
+# 🛡️ Frequently Asked Questions (FAQ)
 
 ## General
 
 ### What is Aegis-Graph?
 
-**Aegis-Graph** is the world's first open-source **Sovereign Academic Audit Protocol**. It uses **Agentic GraphRAG** �a federated swarm of specialized AI agents �to perform deep logical verification of academic credentials. Unlike traditional OCR-based systems, Aegis-Graph verifies the **logical topology** of a credential: whether the institution exists, whether the degree program is real, and whether the timeline is physically possible.
+**Aegis-Graph** is an open-source **Sovereign Academic Audit Protocol** prototype. It uses a pipeline of specialized agents (Vision, Graph, and Logic) to review academic credentials. It verifies whether the institution exists in trusted registries, whether the degree program timeline is consistent, and whether the credential contains expected authenticity markers.
 
 ### Who built Aegis-Graph?
 
-Aegis-Graph is engineered by the Technical Committee at **Atlanta College of Liberal Arts and Sciences (ACLAS College)**, a higher education institution based in Atlanta, Georgia, USA. ACLAS College operates as the primary Gold Standard Sovereign Node in the Aegis-Graph network.
+Aegis-Graph is maintained by the Technical Committee at **Atlanta College of Liberal Arts and Sciences (ACLAS College)**, a higher education institution based in Atlanta, Georgia, USA.
 
 - **Official Website**: [aclas.college](https://aclas.college/)
 - **Contact**: [info@aclas.college](mailto:info@aclas.college)
 
 ### Is Aegis-Graph free to use?
 
-Yes. Aegis-Graph is released under the **CC BY-NC 4.0** (Attribution-NonCommercial) license. Academic institutions and researchers can use, modify, and deploy it freely for non-commercial purposes. Commercial licensing inquiries should be directed to [info@aclas.college](mailto:info@aclas.college).
-
-### How is Aegis-Graph different from traditional verification services?
-
-| Feature | Traditional Services | Aegis-Graph |
-| :--- | :--- | :--- |
-| **Speed** | 5�4 business days | ~6 seconds |
-| **Method** | Manual registrar contact | Autonomous AI agents |
-| **Privacy** | PII shared with third parties | Zero-Knowledge edge processing |
-| **Scope** | Limited database lookups | 250M+ academic records (OpenAlex/ROR) |
-| **Cost** | $15�75 per verification | ~$0.002 per verification |
+Yes. Aegis-Graph is released under the **MIT License**. Academic institutions and researchers can use, modify, and deploy it freely.
 
 ---
 
 ## Technology
 
-### What is Agentic GraphRAG?
-
-**Agentic GraphRAG** is an advanced AI architecture where multiple specialized agents collaborate autonomously to traverse and reason over large knowledge graphs. In Aegis-Graph, three agents work in concert:
-
-1. **Vision Forensics Agent**: Detects synthetic document generation through sub-pixel noise analysis and metadata forensics.
-2. **Graph Navigator Agent**: Performs multi-hop queries across OpenAlex (250M+ scholarly records) and the Research Organization Registry (ROR) to verify institutional legitimacy.
-3. **Logic Auditor Agent**: Uses Chain-of-Thought reasoning to detect temporal paradoxes (e.g., graduating before a program existed) and credit density anomalies.
-
-### What is the 3-Tier Compute Cascade?
+### What is the "Sovereign Academic Graph" (SAG)?
 
-Aegis-Graph processes documents through an escalating pipeline designed to minimize cost:
+The **Sovereign Academic Graph** is our institutional evidence model. It integrates a local index of known institutions with optional real-time queries to global registries like **ROR (Research Organization Registry)** and **OpenAlex**. 
 
-- **Tier 1 (Edge/NPU)**: Free. Handles PII scrubbing and basic structural validation locally. Filters ~15% of low-effort forgeries.
-- **Tier 2 (API)**: ~$0.0001. Queries global academic registries (ROR, OpenAlex). Catches ~60% of diploma mill fraud.
-- **Tier 3 (Cloud LLM)**: ~$0.002. Heavy logical reasoning for the most sophisticated forgeries.
+> **Important:** The presence of an institution in a registry like ROR is evidence that the organization exists, but it is not proof that a specific credential issued in its name is authentic.
 
-This cascade achieves an **85% reduction in token costs** compared to sending every document directly to a cloud LLM.
+### What agents are in the pipeline?
 
-### What is the Model Context Protocol (MCP)?
-
-The **Model Context Protocol (MCP)** is an open-source JSON-RPC standard (originally conceptualized by Anthropic) that Aegis-Graph uses as its communication backbone. MCP allows any institution to plug into the Aegis-Graph network regardless of their preferred LLM provider (OpenAI, Anthropic, Google, or local open-source models like Llama-3).
-
-### What data sources does Aegis-Graph use?
-
-- **[OpenAlex](https://openalex.org/)**: An open catalog of 250M+ scholarly works, authors, and institutions.
-- **[ROR (Research Organization Registry)](https://ror.org/)**: A global, community-curated registry of research organizations.
-- **Sovereign Node Ledgers**: Cryptographic internal databases maintained by participating institutions.
+1. **Vision Forensics Agent**: Performs initial structural analysis of the document (prototype OCR and metadata checks).
+2. **Graph Navigator Agent**: Resolves institutional evidence from local and global registries.
+3. **Logic Auditor Agent**: Performs consistency checks on graduation dates, institution founding years, and known fraud aliases.
 
 ---
 
 ## Privacy & Security
 
-### Does Aegis-Graph store my documents?
-
-**No.** Aegis-Graph implements **RAM-Only Execution**. Uploaded documents are processed entirely in volatile memory and are never written to disk. If the server loses power during processing, no data can be recovered.
+### Does the public dashboard verify my real documents?
 
-### How does Aegis-Graph protect personal information (PII)?
+**No.** The hosted dashboards (on GitHub Pages and Hugging Face Spaces) are **non-production UI demonstrations**. They do not process your file bytes or issue real audit certificates. They are intended to visualize the protocol's reasoning flow only.
 
-The **Privacy-Shield Agent** operates at the institutional edge (on the local NPU/CPU) and scrubs all Personally Identifiable Information (names, ID numbers, addresses) **before** any data is transmitted to cloud-based AI agents. Raw PII never touches the internet.
+### How is privacy handled?
 
-### Is Aegis-Graph compliant with GDPR/FERPA/CCPA?
-
-Yes. The Zero-Trust Edge architecture was specifically designed for compliance:
-- **GDPR** (EU): PII is processed locally and never transferred to third-party cloud providers.
-- **FERPA** (US): Student education records are scrubbed before any external API calls.
-- **CCPA** (California): No persistent storage of personal data.
-
-### What is Zero-Knowledge Privacy in Aegis-Graph?
-
-The protocol's roadmap includes **ZK-Snark** integration (planned for Q4 2026), which will allow institutions to issue cryptographic "Attestation of Degree" proofs �verifying that a degree is legitimate **without revealing the actual transcript contents**. This is the gold standard of privacy-preserving verification.
+The Aegis-Graph architecture is designed for **local processing**. A production deployment should run on an institution's own infrastructure to ensure that Personally Identifiable Information (PII) is never exposed to third-party cloud services without explicit consent and encryption.
 
 ---
 
 ## Integration & Deployment
 
-### How do I deploy Aegis-Graph at my institution?
+### How do I deploy a local node?
 
 ```bash
 # Clone the repository
@@ -114,66 +64,22 @@ cd aegis-graph
 # Install dependencies
 pip install -r requirements.txt
 
-# Configure API keys in .env
-# OPENALEX_API_KEY=your_key
-# OPENAI_API_KEY=your_key
-
-# Run the audit pipeline
-python main_pipeline.py --input path/to/transcript.pdf
+# Run the local auditor pipeline
+python main_pipeline.py
 ```
 
-### Can I integrate Aegis-Graph with my existing Applicant Tracking System (ATS)?
-
-Yes. Aegis-Graph exposes a standard **MCP/JSON-RPC API** that can be integrated into any modern ATS, CRM, or admissions portal. See [Chapter 7: Developer API](en/chapter7-developer-api.md) for full specifications.
-
 ### What are the system requirements?
 
 - **Python**: 3.11+
-- **Hardware**: Any modern CPU; NPU recommended for edge privacy processing.
-- **Browser**: Chrome/Edge (for the verification dashboard).
-- **Network**: Internet access for OpenAlex/ROR queries.
+- **Network**: Internet access is required for ROR/OpenAlex registry lookups.
 
 ---
 
 ## Institutional & Legal
 
-### What is a Sovereign Node?
-
-A **Sovereign Node** is a cryptographically secured server operated by a verified institution. When a document claims to originate from that institution, the Sovereign Node can perform instant, deterministic verification against its internal cryptographic ledger �completing the audit in under 150 milliseconds.
-
-### How can my university join the Aegis-Graph network?
-
-Institutions interested in deploying their own Sovereign Node should contact the ACLAS Technical Committee at [info@aclas.college](mailto:info@aclas.college). The onboarding process includes cryptographic key generation and MCP endpoint configuration.
-
 ### Is ACLAS College an accredited institution?
 
-**Atlanta College of Liberal Arts and Sciences (ACLAS College)** is a higher education institution based in Atlanta, Georgia, USA. For detailed accreditation and program information, please visit the official website at [aclas.college](https://aclas.college/).
-
----
-
-## Community & Contribution
-
-### How can I contribute to Aegis-Graph?
-
-We welcome contributions from developers worldwide. Please see our [Contributing Guide](https://github.com/aclascollege/aegis-graph/blob/main/CONTRIBUTING.md) for detailed instructions on submitting issues, feature requests, and pull requests.
-
-### How do I report a security vulnerability?
-
-Please do **not** open a public issue. Instead, email our security team at [info@aclas.college](mailto:info@aclas.college). We follow a coordinated disclosure policy with a 48-hour response commitment. See our [Security Policy](https://github.com/aclascollege/aegis-graph/blob/main/SECURITY.md).
-
-### Where can I follow ACLAS College updates?
-
-- **X (Twitter)**: [@aclascollege](https://x.com/aclascollege)
-- **LinkedIn**: [ACLAS College](https://www.linkedin.com/school/aclas-college/)
-- **GitHub**: [github.com/aclascollege](https://github.com/aclascollege)
-
----
-
-## Related Projects
-
-### What is Neuro-Edu?
-
-**[Neuro-Edu](https://github.com/aclascollege/neuro-edu)** is another open-source project by ACLAS College �an AI-powered educational sandbox designed for sovereign, privacy-preserving learning environments. Together with Aegis-Graph, it forms the core of the ACLAS sovereign AI ecosystem.
+**Atlanta College of Liberal Arts and Sciences (ACLAS College)** is a higher education institution based in Atlanta, Georgia, USA. For detailed information regarding our programs, please visit our official website at [aclas.college](https://aclas.college/).
 
 ---
 

docs/zh/README.md

@@ -4,27 +4,27 @@
   <img src="../../assets/hero-banner.png" alt="Aegis-Graph Banner" width="100%">
 </div>
 
-欢迎阅读 **Aegis-Graph** 官方技术文档。Aegis-Graph 是一项主权级学术审计协议，旨在为全球教育体系提供去中心化的、高诚信度的验证方案。本手册将深入探讨驱动该协议的架构设计、多智能体框架及数据生态系统。
+欢迎阅读 **Aegis-Graph** 官方技术文档。Aegis-Graph 是一项主权级学术审计协议，旨在为全球教育体系提供去中心化的、高诚信度的验证方案。本手册将深入探讨驱动该协议的架构设计、多智能体框架及机构图谱证据模型。
 
 ---
 
 ## 🏛️ 执行摘要
 
-**Aegis-Graph** 是专为检测学术造假及 AI 生成凭证篡改而设计的专用多智能体框架。该协议由 **AEGIS-GRAPH 全球治理委员会** 监管，并由 **亚特兰大文理学院 (ACLAS)** 提供核心技术支持。它利用 **智能体图谱 RAG (Agentic GraphRAG)** 技术，确保全球教育领域进入主权诚信时代。
+**Aegis-Graph** 是一个专为检测学术造假及 AI 生成凭证篡改而设计的开源多智能体框架原型。该协议由 **AEGIS-GRAPH 全球治理委员会** 监管，并由 **亚特兰大文理学院 (ACLAS)** 提供核心支持。它利用 **智能体图谱 RAG (Agentic GraphRAG)** 技术处理证据，取代传统的人工验证流程。
 
 ## 🧩 文档核心板块
 
-### [1. 核心架构设计](chapter2-arch.md)
-探索其 **深度防御 (Defense-in-Depth)** 模型，包括数据摄取层、图谱 RAG 推理引擎及共识协议。
+### [1. 核心架构设计](chapter2.md)
+探索其 **深度防御 (Defense-in-Depth)** 模型，包括数据摄取层、图谱 RAG 证据引擎及逻辑审计共识协议。
 
-### [2. 多智能体推理群 (MARS)](chapter3-agents.md)
+### [2. 多智能体推理群 (MARS)](chapter3.md)
 深入了解负责审计握手的专用 AI 智能体（视觉法证、图谱导航及逻辑审计）。
 
-### [3. 主权学术图谱 (SAG)](chapter4.md)
-详细披露包含 102,482 个机构节点的全球注册表，整合了 ROR、OpenAlex 及 AEGIS 主权账本。
+### [3. 机构证据模型 (SAG)](chapter4.md)
+详细披露我们的证据模型，该模型整合了本地机构索引以及可选的 ROR 和 OpenAlex 注册表证据。
 
 ### [4. 部署与集成指南](chapter8.md)
-关于启动本地节点、连接全球注册表及 API 集成的分步说明。
+关于启动本地节点、环境配置及管道集成的分步说明。
 
 ---
 
@@ -32,10 +32,10 @@
 
 | 阶段 | 里程碑 | 状态 |
 | :--- | :--- | :--- |
-| **V1.0** | 初始节点注册表 (102K 机构) | ✅ 已完成 |
-| **V2.0** | MARS 多智能体推理框架 | ✅ 已完成 |
-| **V2.5** | 零知识证据 (ZKE) 隐私模型 | 🚧 开发中 |
-| **V3.0** | 全去中心化主权治理 | 📅 规划中 |
+| **V1.0** | 机构索引集成 | ✅ 已完成 |
+| **V2.0** | MARS 多智能体推理框架原型 | ✅ 已完成 |
+| **V2.5** | 证据加权逻辑审计 | ✅ 已完成 |
+| **V3.0** | 服务端签名的审计证书 | 🚧 进行中 |
 
 ---
 

docs/zh/chapter2.md

@@ -1,26 +1,30 @@
 # 第2章：核心架构设计
 
-Aegis-Graph 并非一个简单的数据库，而是一个基于 **智能体图谱 RAG (Agentic GraphRAG)** 的分布式核验协议。其架构设计遵循“深度防御”原则。
+Aegis-Graph 并非一个简单的数据库，而是一个基于 **智能体图谱 RAG (Agentic GraphRAG)** 的分布式证据核验协议。其架构设计遵循“深度防御”原则。
 
 ## 🏗️ 架构三层模型
 
 ### 1. 证据摄取层 (Evidence Ingestion Layer)
-负责提取数字凭证中的元数据。该层利用多模态 AI 对 PDF、图像和数字证书进行解析，提取签发者、持有者及学术指标。
+负责提取数字凭证中的元数据。该层利用 AI 对 PDF 和图像进行初步解析，提取签发机构、日期及学术内容。
 
-### 2. MARS 推理层 (MARS Reasoning Layer)
-这是协议的核心。**多智能体推理群 (MARS)** 针对摄取的证据执行并行审计。不同智能体从视觉、图谱和逻辑三个维度进行“背对背”验证。
+### 2. 证据推理层 (Evidence Reasoning Layer)
+这是协议的核心。**多智能体推理群 (MARS)** 针对摄取的证据执行并行审计。不同智能体从视觉、图谱和逻辑三个维度进行交叉验证。
 
-### 3. 主权账本层 (Sovereign Ledger Layer)
-核验结果通过共识后，将生成加密证明并锚定到主权账本。这确保了核验路径的不可篡改性和可追溯性。
+### 3. 审计报告层 (Audit Reporting Layer)
+核验结果通过共识后，将生成审计报告。在生产环境中，该报告应包含加密签名，以确保核验路径的不可篡改性和可追溯性。
 
 ---
 
 ## 🧩 关键技术：Agentic GraphRAG
 
-Aegis-Graph 创新性地结合了 **图谱数据库 (Graph Database)** 和 **智能体推理 (Agentic Reasoning)**：
+Aegis-Graph 结合了 **图谱证据模型 (Graph Evidence Model)** 和 **智能体推理 (Agentic Reasoning)**：
 
-*   **动态图谱**：整合 ROR、OpenAlex 等全球数据，构建包含 102,482 个节点的实时学术地图。
-*   **智能体导航**：智能体不是简单的检索数据，而是像“法证专家”一样在图谱中寻找关联证据，排除潜在的造假路径。
+*   **动态图谱**：整合 ROR、OpenAlex 等全球公开数据，构建实时的机构证据地图。
+*   **智能体导航**：智能体在图谱中寻找关联证据（如机构状态、历史记录），为逻辑审计提供背景支持。
 
 ---
-*返回 [文档首页](../README.md)*
+> [!IMPORTANT]
+> **生产状态说明：** 专业核验需要服务端文档解析、发行方证据检查、撤销检查以及签名的审计响应。
+
+---
+*返回 [文档首页](README.md)*

docs/zh/chapter3.md

@@ -1,33 +1,48 @@
 # 第3章：MARS 多智能体框架
 
-**多智能体推理群 (MARS)** 是 Aegis-Graph 协议的去中心化大脑。该集群由专门设计的主权智能实体组成，通过协议握手达成审计共识。
+**多智能体推理群 (MARS)** 是 Aegis-Graph 协议的推理核心。该集群由专门设计的智能代理组成，通过协作达成审计共识。
 
 ## 👁️ 智能体 Alpha：视觉法证 (VF)
-VF 智能体负责数字遗迹的像素级分析。
+VF 智能体负责对数字凭证进行初步的结构化分析。
 
-*   **技术规格**：基于优化后的 ResNet-50 骨干网络，配备针对文档造假的自定义注意力层。
-*   **检测维度**：
-    *   **扩散伪迹**：识别 Stable Diffusion 等模型生成的典型高频噪声。
-    *   **矢量一致性**：分析 PDF 对象中的字间距、字体粗细及 SVG 路径完整性。
-    *   **印章法证**：将机构印章与包含 4 万多个官方戳记的数据库进行比对。
+### 当前范围 (原型)
+*   **结构提取**：识别印章、抬头及签名行等关键布局元素。
+*   **OCR 规范化**：将视觉信息转化为语义元数据，供推理层使用。
+*   **布局检测**：识别明显的文档布局不一致性（像素级 AI 防伪是路线图功能）。
 
 ---
 
 ## 🗺️ 智能体 Beta：图谱导航 (GN)
-GN 智能体负责在 **主权学术图谱 (SAG)** 中定位机构背景。
+GN 智能体负责解析机构证据，为凭证审计提供背景。
 
-*   **身份解析**：通过 ROR 和 OpenAlex 验证签发者的全球唯一身份。
-*   **血缘映射**：追踪机构的更名、合并或撤销历史。
-*   **学术足迹**：交叉引用全球出版指标，确保签发机构在学术生态中处于活跃状态。
+### 功能
+*   **身份解析**：通过 ROR 和 OpenAlex 验证签发机构的全球身份。
+*   **血缘映射**：追踪机构的更名、合并或撤销历史，确保时间轴一致性。
+*   **证据提供**：提供机构在官方注册表中的存在性及状态证据。
 
 ---
 
 ## ⚖️ 智能体 Gamma：逻辑审计 (LA)
-LA 智能体是集群的“首席大法官”，负责跨层推理和悖论检测。
+LA 智能体负责跨层证据推理和逻辑一致性检查。
 
-*   **时间悖论检查**：确保学位授予日期与机构的运营时间轴对齐。
-*   **课程真实性**：验证特定学位项目在对应时期是否存在于该机构的认证目录中。
-*   **共识编排**：汇总 VF 和 GN 的证据，并启动 **思维链 (CoT)** 推理来解决任何冲突。
+### 审计逻辑
+*   **时间一致性**：确保凭证日期与机构的运营时间轴对齐。
+*   **欺诈检测**：对照已知欺诈机构列表及黑名单别名进行核验。
+*   **共识编排**：汇总 VF 和 GN 的发现。如果出现证据冲突，LA 智能体将启动 **思维链 (CoT)** 推理来确定最终风险评分。
 
 ---
-*返回 [文档首页](../README.md)*
+
+## 🤝 审计握手
+最终的审计结论基于 MARS 集群的累积证据。
+
+1. **摄取**：对文档数据进行规范化。
+2. **并行审计**：各智能体执行专门的证据检查。
+3. **共识达成**：逻辑审计代理解决矛盾并计算最终证据权重。
+4. **报告生成**：生成详细的审计推理追踪报告。
+
+---
+> [!IMPORTANT]
+> **生产状态说明：** 专业核验需要服务端文档解析、发行方证据检查、撤销检查以及签名的审计响应。
+
+---
+*返回 [文档首页](README.md)*

docs/zh/chapter4.md

@@ -1,37 +1,38 @@
-# 第4章：主权学术图谱 (SAG)
+# 第4章：机构证据模型 (SAG)
 
-**主权学术图谱 (SAG)** 是 Aegis-Graph 协议的权威全球注册表。它由超过 **102,482 个已验证的机构节点** 及数百万个关联边缘组成。
+**主权学术图谱 (SAG)** 是 Aegis-Graph 协议中的机构证据层。它将本地维护的机构索引与全球公共注册表（如 ROR 和 OpenAlex）相结合，为凭证审计提供必要的背景信息。
 
 ## 📊 数据拓扑结构
 
-SAG 并非静态数据库，而是一个动态的、多层级的图谱，整合了全球顶级学术注册表的数据。
+SAG 并不是一个证明凭证真实性的“判决数据库”，而是一个提供机构背景证据的动态模型。
 
-### 核心数据源
-| 来源 | 贡献内容 |
+### 核心证据源
+| 来源 | 作用 |
 | :--- | :--- |
-| **ROR** | 主要的研究机构 ID 和机构元数据。 |
-| **OpenAlex** | 学术足迹、出版指标及机构影响力。 |
-| **Crossref** | DOI 级别的机构关联和元数据准确性。 |
-| **AEGIS 账本** | 高权威主权节点元数据及历史认证记录。 |
+| **本地索引** | 缓存高信誉机构的元数据、黑名单别名及已知欺诈特征。 |
+| **ROR** | 提供全球研究机构的标准化身份（ROR ID）及运营状态。 |
+| **OpenAlex** | 提供机构的学术产出背景及影响力指标作为辅助证据。 |
 
 ---
 
-## 🏛️ 节点解剖
-SAG 中的每个机构节点都包含主权审计所需的丰富属性：
+## 🏛️ 证据逻辑
 
-*   **时间边界**：成立日期、运营状态及撤销历史。
-*   **地理矢量**：精确的物理校区坐标，用于检测地理欺诈（Spoofing）。
-*   **签发者指纹**：加密身份和公钥，用于数字签名验证。
-*   **层级边缘**：母校、分校、研究机构之间的关联关系。
+在审计过程中，SAG 的作用是回答以下问题：
+1. **机构存在性**：该机构是否在公认的全球注册表中有记录？
+2. **生命周期一致性**：凭证的签发日期是否在机构的运营期限内？
+3. **状态验证**：该机构当前是否处于活跃状态，或者已被标记为撤销/欺诈？
+
+> [!IMPORTANT]
+> **特别说明：** 机构在 ROR 等注册表中的存在仅证明该组织实体是真实的，**不代表**任何声称由该机构签发的凭证自动具有真实性。
 
 ---
 
-## ⚡ 索引与性能
-为了实现亚秒级的全球核验响应，Aegis-Graph 采用了高性能索引策略：
+## ⚡ 索引与匹配
 
-1.  **矢量化搜索**：机构名称和元数据经过矢量化处理，允许对拼写变体或微小差异进行模糊匹配。
-2.  **分布式缓存**：高频机构节点被缓存在边缘节点层，实现近乎瞬时的解析。
-3.  **交叉核验**：所有节点定期在多个全球注册表中重新验证，确保数据的新鲜度和完整性。
+为了提高证据解析的准确性，Aegis-Graph 采用了以下策略：
+1. **标准化处理**：对机构名称进行规范化，消除拼写差异或符号影响。
+2. **多因子匹配**：结合地理位置、成立年份及官方域名进行交叉比对。
+3. **证据加权**：匹配结果被赋予置信度分数，作为 LogicAuditor 最终决策的重要输入。
 
 ---
-*返回 [文档首页](../README.md)*
+*返回 [文档首页](README.md)*