Initial commit of TruthCheck with Cyber-Noir UI

.gitignore

@@ -0,0 +1,13 @@
+venv/
+
+__pycache__/
+
+*.pyc
+
+.env
+
+db.sqlite3
+
+history.db
+
+*.log

.vscode/launch.json

@@ -0,0 +1,12 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "TruthCheck Gradio",
+            "type": "python",
+            "request": "launch",
+            "program": "run.py",
+            "console": "integratedTerminal"
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,9 @@
+{
+    "python.defaultInterpreterPath": "./venv/bin/python",
+    "python.terminal.activateEnvironment": true,
+    "files.exclude": {
+        "**/__pycache__": true,
+        "**/*.pyc": true
+    },
+    "html.autoClosingTags": false
+}

README.md

@@ -0,0 +1,2 @@
+# TruthCheck-App
+An intelligent fact-checking tool would not only help users verify the accuracy of digital content instantly but also foster greater transparency and accountability in online communication..

app.py

@@ -0,0 +1,293 @@
+# app.py
+import os
+from flask import Flask, render_template, request, jsonify
+from functools import lru_cache
+import hashlib
+import sqlite3
+import datetime
+import json
+
+from models.claim_extractor import ClaimExtractor
+from models.keyword_extractor import KeywordExtractor
+from models.evidence_retriever import EvidenceRetriever
+from models.nli_classifier import NLIClassifier
+from utils.similarity import calculate_similarity
+from utils.config import Config
+
+
+# Initialize models globally
+claim_extractor = ClaimExtractor()
+keyword_extractor = KeywordExtractor()
+evidence_retriever = EvidenceRetriever()
+nli_classifier = NLIClassifier()
+
+
+class TruthCheckSystem:
+    def __init__(self):
+        self.claim_extractor = claim_extractor
+        self.keyword_extractor = keyword_extractor
+        self.evidence_retriever = evidence_retriever
+        self.nli_classifier = nli_classifier
+        self.cache = {}
+        
+    def _get_cache_key(self, text):
+        """Generate cache key for claim"""
+        return hashlib.md5(text.encode()).hexdigest()
+    
+    def verify_claim(self, text):
+        """
+        Enhanced fact verification with multi-evidence aggregation
+        and consensus mechanism (similar to FactCheck system)
+        """
+        try:
+            # Check cache
+            cache_key = self._get_cache_key(text)
+            if cache_key in self.cache:
+                print("Returning cached result")
+                return self.cache[cache_key]
+            
+            # Step 1: Extract claims
+            claims = self.claim_extractor.extract_claims(text)
+            if not claims:
+                result = ("Low Confidence", 0.3, "No valid claims found. Please provide a clear factual statement.")
+                self.cache[cache_key] = result
+                return result
+            
+            claim = claims[0]
+            
+            # Step 2: Extract keywords
+            keywords = self.keyword_extractor.extract_keywords(claim)
+            
+            # Step 3: Retrieve evidence from multiple sources
+            evidence_items = self.evidence_retriever.get_evidence(keywords)
+            
+            if not evidence_items:
+                result = ("Low Confidence", 0.3, "Not enough reliable evidence found.")
+                self.cache[cache_key] = result
+                return result
+            
+            # Step 4: Filter by semantic similarity
+            relevant_evidence = []
+            for item in evidence_items:
+                similarity = calculate_similarity(claim, item['content'])
+                if similarity > Config.SIMILARITY_THRESHOLD:
+                    item['similarity_score'] = similarity
+                    relevant_evidence.append(item)
+            
+            if not relevant_evidence:
+                result = ("Low Confidence", 0.4, "No semantically relevant evidence found.")
+                self.cache[cache_key] = result
+                return result
+            
+            # Step 5: Sort by combined score (credibility + similarity)
+            for item in relevant_evidence:
+                item['combined_score'] = (
+                    item.get('credibility_score', 0.5) * 0.6 +
+                    item.get('similarity_score', 0.5) * 0.4
+                )
+            
+            relevant_evidence.sort(key=lambda x: x['combined_score'], reverse=True)
+            
+            # Step 6: Multi-Evidence NLI with Consensus Mechanism
+            # Use top 4 evidence sources (as per FactCheck research)
+            top_evidence = relevant_evidence[:4]
+            
+            nli_results = []
+            for evidence_item in top_evidence:
+                nli_result = self.nli_classifier.classify(claim, evidence_item['content'])
+                nli_results.append({
+                    'nli': nli_result,
+                    'credibility': evidence_item.get('credibility_score', 0.5),
+                    'similarity': evidence_item.get('similarity_score', 0.5),
+                    'source': evidence_item.get('source', 'Unknown'),
+                    'url': evidence_item.get('url', '')
+                })
+            
+            # Step 7: Weighted Consensus Voting
+            entailment_score = 0
+            contradiction_score = 0
+            neutral_score = 0
+            
+            total_weight = 0
+            for result in nli_results:
+                # Weight by credibility and confidence
+                weight = result['credibility'] * result['nli']['confidence']
+                total_weight += weight
+                
+                if result['nli']['label'] == 'ENTAILMENT':
+                    entailment_score += weight
+                elif result['nli']['label'] == 'CONTRADICTION':
+                    contradiction_score += weight
+                else:
+                    neutral_score += weight
+            
+            # Normalize scores
+            if total_weight > 0:
+                entailment_score /= total_weight
+                contradiction_score /= total_weight
+                neutral_score /= total_weight
+            
+            # Step 8: Determine final label with consensus threshold
+            consensus_threshold = 0.6  # Require 60% agreement
+            
+            max_score = max(entailment_score, contradiction_score, neutral_score)
+            
+            if max_score == entailment_score and entailment_score >= consensus_threshold:
+                label = "True"
+                final_confidence = entailment_score
+            elif max_score == contradiction_score and contradiction_score >= consensus_threshold:
+                label = "False"
+                final_confidence = contradiction_score
+            else:
+                label = "Low Confidence"
+                final_confidence = max(entailment_score, contradiction_score, neutral_score)
+            
+            # Step 9: Prepare evidence summary
+            evidence_summary = self._format_evidence_summary(nli_results, top_evidence)
+            
+            result = (label, final_confidence, evidence_summary)
+            
+            # Cache result
+            self.cache[cache_key] = result
+            
+            return result
+            
+        except Exception as e:
+            print(f"Error during claim verification: {e}")
+            import traceback
+            traceback.print_exc()
+            return ("Error", 0.0, f"An internal error occurred: {str(e)}")
+    
+    def _format_evidence_summary(self, nli_results, evidence_items):
+        """Format evidence summary with sources and verdicts"""
+        summary_parts = []
+        
+        summary_parts.append(f"**Analyzed {len(nli_results)} sources:**\n")
+        
+        for i, (nli_res, evidence) in enumerate(zip(nli_results, evidence_items), 1):
+            source = nli_res['source']
+            verdict = nli_res['nli']['label']
+            confidence = nli_res['nli']['confidence']
+            credibility = nli_res['credibility']
+            url = nli_res['url']
+            
+            # Get snippet
+            content = evidence.get('content', '')[:300]
+            
+            summary_parts.append(
+                f"\n**Source {i}: {source}**\n"
+                f"Verdict: {verdict} (Confidence: {confidence:.2%})\n"
+                f"Credibility Score: {credibility:.2f}\n"
+                f"Excerpt: {content}...\n"
+                f"URL: {url}\n"
+            )
+        
+        return "\n".join(summary_parts)
+
+
+# Initialize system
+truthcheck_system_instance = TruthCheckSystem()
+
+def init_db():
+    """Initialize SQLite database"""
+    conn = sqlite3.connect('history.db')
+    c = conn.cursor()
+    c.execute('''
+        CREATE TABLE IF NOT EXISTS verifications (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            claim TEXT NOT NULL,
+            label TEXT NOT NULL,
+            confidence REAL,
+            date TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        )
+    ''')
+    conn.commit()
+    conn.close()
+
+init_db()
+
+
+def create_app():
+    app = Flask(__name__, static_folder='static', template_folder='templates')
+    app.config['SECRET_KEY'] = os.environ.get('SECRET_KEY', Config.SECRET_KEY)
+    app.config['DEBUG'] = Config.DEBUG
+    
+    @app.route('/')
+    def index():
+        return render_template('index.html')
+
+    @app.route('/how-it-works')
+    def how_it_works():
+        return render_template('how_it_works.html')
+
+    @app.route('/api-docs')
+    def api_docs():
+        return render_template('api.html')
+    
+    @app.route('/dashboard')
+    def dashboard():
+        return render_template('dashboard.html')
+
+    @app.route('/api/history')
+    def get_history():
+        try:
+            conn = sqlite3.connect('history.db')
+            conn.row_factory = sqlite3.Row
+            c = conn.cursor()
+            c.execute('SELECT * FROM verifications ORDER BY date DESC LIMIT 50')
+            rows = c.fetchall()
+            conn.close()
+            
+            history = []
+            for row in rows:
+                history.append({
+                    'id': row['id'],
+                    'claim': row['claim'],
+                    'label': row['label'],
+                    'confidence': row['confidence'],
+                    'date': row['date']
+                })
+            return jsonify(history)
+        except Exception as e:
+            return jsonify({'error': str(e)}), 500
+
+    @app.route('/api/verify', methods=['POST'])
+    def verify_claim_api():
+        try:
+            data = request.get_json()
+            claim_text = data.get('claim', '')
+            
+            if not claim_text:
+                return jsonify({'error': 'No claim provided'}), 400
+            
+            label, confidence, evidence = truthcheck_system_instance.verify_claim(claim_text)
+            
+            # Save to DB
+            try:
+                conn = sqlite3.connect('history.db')
+                c = conn.cursor()
+                c.execute('INSERT INTO verifications (claim, label, confidence) VALUES (?, ?, ?)',
+                          (claim_text, label, float(confidence)))
+                conn.commit()
+                conn.close()
+            except Exception as e:
+                print(f"DB Error: {e}")
+            
+            result = {
+                'label': label,
+                'confidence': round(confidence, 3),
+                'evidence': evidence,
+                'claim': claim_text
+            }
+            
+            return jsonify(result)
+            
+        except Exception as e:
+            print(f"API error: {e}")
+            return jsonify({'error': f'Server error: {str(e)}'}), 500
+    
+    @app.route('/health')
+    def health_check():
+        return jsonify({'status': 'healthy', 'message': 'TruthCheck is running.'})
+    
+    return app

curl.exe

@@ -0,0 +1,3 @@
+curl.exe -X POST http://127.0.0.1:5000/api/verify `
+  -H "Content-Type: application/json" `
+  -d "{\"claim\": \"The sun is a star.\"}"

google_search.py

@@ -0,0 +1,26 @@
+# google_search.py
+
+class SearchResult:
+    def __init__(self, snippet, url, source_title=None):
+        self.snippet = snippet
+        self.url = url
+        self.source_title = source_title
+
+class SearchResponse:
+    def __init__(self, results):
+        self.results = results
+
+def search(queries, num_results=3):
+    """Mock search function returning dummy data for testing."""
+    responses = []
+    for query in queries:
+        dummy_results = [
+            SearchResult(
+                snippet=f"This is a mock snippet for query '{query}' - result {i+1}.",
+                url=f"https://example.com/{query.replace(' ', '_')}/{i}",
+                source_title="Mock News Source"
+            )
+            for i in range(num_results)
+        ]
+        responses.append(SearchResponse(results=dummy_results))
+    return responses

models/__init__.py

@@ -0,0 +1,4 @@
+"""
+TruthCheck Models Package
+Contains all the NLP and ML models for fact-checking
+"""

models/claim_extractor.py

@@ -0,0 +1,34 @@
+# models/claim_extractor.py
+import re
+import spacy
+
+class ClaimExtractor:
+    def __init__(self): # Corrected __init__
+        try:
+            self.nlp = spacy.load("en_core_web_sm")
+        except OSError:
+            print("Please install spaCy English model: python -m spacy download en_core_web_sm")
+            raise
+    
+    def extract_claims(self, text):
+        """Extract factual claims from text"""
+        if not text or len(text.strip()) < 10:
+            return []
+        
+        # Use spaCy for sentence segmentation
+        doc = self.nlp(text)
+        claims = []
+        
+        for sent in doc.sents:
+            sentence = sent.text.strip()
+            
+            # Filter out questions, commands, and short sentences
+            if (len(sentence.split()) > 5 and 
+                not sentence.endswith('?') and 
+                not sentence.startswith(('How', 'What', 'When', 'Where', 'Why', 'Who')) and
+                not re.match(r'^(Please|Let|Can you)', sentence, re.IGNORECASE)):
+                
+                claims.append(sentence)
+        
+        return claims if claims else [text.strip()]
+

models/evidence_retriever.py

@@ -0,0 +1,206 @@
+# models/evidence_retriever.py
+import wikipedia
+import requests
+from bs4 import BeautifulSoup
+import time
+from urllib.parse import quote_plus
+
+
+class EvidenceRetriever:
+    def __init__(self):
+        self.wikipedia_timeout = 10
+        self.max_evidence_sources = 10
+        self.trusted_domains = [
+            'reuters.com', 'apnews.com', 'bbc.com', 'nature.com',
+            'science.org', 'who.int', 'cdc.gov', 'nasa.gov', 
+            'wikipedia.org', '.gov', '.edu'
+        ]
+        
+    def get_evidence(self, keywords):
+        """Retrieve evidence from multiple sources with credibility scoring"""
+        evidence = []
+        
+        # Get evidence from Wikipedia (most reliable)
+        wiki_evidence = self._get_wikipedia_evidence(keywords)
+        evidence.extend(wiki_evidence)
+        
+        # Get evidence from web search (using Google Custom Search as fallback)
+        web_evidence = self._get_web_search_evidence(keywords)
+        evidence.extend(web_evidence)
+        
+        # Sort by credibility score and return top sources
+        evidence.sort(key=lambda x: x.get('credibility_score', 0.0), reverse=True)
+        
+        return evidence[:10]
+    
+    def _assign_credibility_score(self, source_type, url):
+        """Assign credibility scores based on source type and domain"""
+        if 'wikipedia.org' in url:
+            return 0.95
+        elif any(url.endswith(gov) for gov in ['.gov', '.gov/']):
+            return 0.92
+        elif any(url.endswith(edu) for edu in ['.edu', '.edu/']):
+            return 0.88
+        elif any(trusted in url for trusted in ['reuters.com', 'apnews.com', 'bbc.com']):
+            return 0.85
+        elif any(sci in url for sci in ['nature.com', 'science.org', 'ncbi.nlm.nih.gov']):
+            return 0.90
+        elif source_type == 'wikipedia':
+            return 0.95
+        elif source_type == 'academic':
+            return 0.88
+        elif source_type == 'government':
+            return 0.92
+        elif source_type == 'news_trusted':
+            return 0.80
+        else:
+            return 0.60
+    
+    def _get_wikipedia_evidence(self, keywords):
+        """Retrieve evidence from Wikipedia"""
+        evidence = []
+        
+        try:
+            search_terms = ' '.join(keywords[:4])
+            search_results = wikipedia.search(search_terms, results=5)
+            
+            for title in search_results:
+                try:
+                    summary = wikipedia.summary(title, sentences=7, auto_suggest=False)
+                    url = f'https://en.wikipedia.org/wiki/{title.replace(" ", "_")}'
+                    
+                    evidence.append({
+                        'content': summary,
+                        'source': f'Wikipedia - {title}',
+                        'url': url,
+                        'credibility_score': self._assign_credibility_score('wikipedia', url),
+                        'source_type': 'wikipedia'
+                    })
+                    
+                    if len(evidence) >= 3:
+                        break
+                        
+                except (wikipedia.DisambiguationError, wikipedia.PageError):
+                    continue
+                    
+        except Exception as e:
+            print(f"Wikipedia search error: {e}")
+        
+        return evidence
+    
+    def _get_web_search_evidence(self, keywords):
+        """Retrieve evidence from web search using SearXNG metasearch"""
+        evidence = []
+        
+        try:
+            query = ' '.join(keywords[:5])
+            
+            # Method 1: Try DuckDuckGo Lite (more reliable)
+            ddg_results = self._search_duckduckgo_lite(query)
+            evidence.extend(ddg_results)
+            
+            # Method 2: If DuckDuckGo fails, use direct scraping with Google
+            if len(evidence) < 3:
+                google_results = self._search_google_scrape(query)
+                evidence.extend(google_results)
+            
+        except Exception as e:
+            print(f"Web search error: {e}")
+        
+        return evidence[:5]
+    
+    def _search_duckduckgo_lite(self, query):
+        """Search using DuckDuckGo Lite (HTML version, more stable)"""
+        results = []
+        
+        try:
+            url = "https://lite.duckduckgo.com/lite/"
+            data = {"q": query}
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+            }
+            
+            response = requests.post(url, data=data, headers=headers, timeout=10)
+            
+            if response.status_code == 200:
+                soup = BeautifulSoup(response.text, 'html.parser')
+                
+                # Find all result rows
+                result_table = soup.find_all('tr')
+                
+                for row in result_table[:10]:
+                    try:
+                        link = row.find('a', class_='result-link')
+                        snippet_td = row.find('td', class_='result-snippet')
+                        
+                        if link and snippet_td:
+                            result_url = link.get('href', '')
+                            title = link.get_text(strip=True)
+                            snippet = snippet_td.get_text(strip=True)
+                            
+                            if result_url and snippet:
+                                results.append({
+                                    'content': snippet,
+                                    'source': f'Web - {title}',
+                                    'url': result_url,
+                                    'credibility_score': self._assign_credibility_score('web', result_url),
+                                    'source_type': 'web'
+                                })
+                                
+                                if len(results) >= 3:
+                                    break
+                    except:
+                        continue
+                        
+        except Exception as e:
+            print(f"DuckDuckGo Lite error: {e}")
+        
+        return results
+    
+    def _search_google_scrape(self, query):
+        """Search using Google scraping (fallback method)"""
+        results = []
+        
+        try:
+            url = f"https://www.google.com/search?q={quote_plus(query)}"
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+            }
+            
+            response = requests.get(url, headers=headers, timeout=10)
+            
+            if response.status_code == 200:
+                soup = BeautifulSoup(response.text, 'html.parser')
+                
+                # Find search results
+                search_results = soup.find_all('div', class_='g')
+                
+                for result in search_results[:5]:
+                    try:
+                        link = result.find('a')
+                        snippet_div = result.find('div', class_=['VwiC3b', 'lEBKkf'])
+                        
+                        if link and snippet_div:
+                            result_url = link.get('href', '')
+                            title = result.find('h3')
+                            title_text = title.get_text(strip=True) if title else 'Unknown'
+                            snippet = snippet_div.get_text(strip=True)
+                            
+                            if result_url.startswith('http') and snippet:
+                                results.append({
+                                    'content': snippet,
+                                    'source': f'Web - {title_text}',
+                                    'url': result_url,
+                                    'credibility_score': self._assign_credibility_score('web', result_url),
+                                    'source_type': 'web'
+                                })
+                                
+                                if len(results) >= 3:
+                                    break
+                    except:
+                        continue
+                        
+        except Exception as e:
+            print(f"Google scrape error: {e}")
+        
+        return results

models/keyword_extractor.py

@@ -0,0 +1,40 @@
+# models/keyword_extractor.py
+import spacy
+from collections import Counter
+
+class KeywordExtractor:
+    def __init__(self): # Corrected __init__
+        try:
+            self.nlp = spacy.load("en_core_web_sm")
+        except OSError:
+            print("Please install spaCy English model: python -m spacy download en_core_web_sm")
+            raise
+    
+    def extract_keywords(self, text):
+        """Extract keywords and named entities from text"""
+        doc = self.nlp(text)
+        
+        keywords = []
+        
+        # Extract named entities
+        for ent in doc.ents:
+            if ent.label_ in ['PERSON', 'ORG', 'GPE', 'PRODUCT', 'EVENT', 'DATE']:
+                keywords.append(ent.text)
+        
+        # Extract noun phrases and important words
+        for chunk in doc.noun_chunks:
+            if len(chunk.text.split()) <= 3:  # Avoid very long phrases
+                keywords.append(chunk.text)
+        
+        # Extract individual important words
+        for token in doc:
+            if (token.pos_ in ['NOUN', 'PROPN'] and 
+                not token.is_stop and 
+                not token.is_punct and 
+                len(token.text) > 2):
+                keywords.append(token.text)
+        
+        # Remove duplicates and return most common
+        keyword_counts = Counter(keywords)
+        return [word for word, count in keyword_counts.most_common(10)]
+

models/nli_classifier.py

@@ -0,0 +1,182 @@
+# models/nli_classifier.py
+from transformers import pipeline
+import torch
+from collections import Counter
+
+
+class NLIClassifier:
+    _instance = None
+    _initialized = False
+    
+    def __new__(cls):
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+        return cls._instance
+    
+    def __init__(self):
+        if self._initialized:
+            return
+        
+        try:
+            print("Loading NLI models (this may take a moment)...")
+            device = 0 if torch.cuda.is_available() else -1
+            
+            self.models = []
+            
+            # Model 1: RoBERTa-large-MNLI (most accurate)
+            try:
+                self.models.append({
+                    'name': 'roberta-large-mnli',
+                    'pipeline': pipeline(
+                        "text-classification",
+                        model="roberta-large-mnli",
+                        device=device
+                    ),
+                    'weight': 0.5
+                })
+                print("✓ Loaded RoBERTa-large-MNLI")
+            except Exception as e:
+                print(f"⚠ Failed to load RoBERTa-large-MNLI: {e}")
+            
+            # Model 2: DeBERTa-v3-large MNLI fine-tuned (use pre-trained version)
+            try:
+                self.models.append({
+                    'name': 'deberta-v3-large-mnli',
+                    'pipeline': pipeline(
+                        "text-classification",
+                        model="MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli",
+                        device=device
+                    ),
+                    'weight': 0.5
+                })
+                print("✓ Loaded DeBERTa-v3-large-MNLI")
+            except Exception as e:
+                print(f"⚠ Failed to load DeBERTa-v3-large-MNLI: {e}")
+            
+            if not self.models:
+                # Fallback to BART if both fail
+                try:
+                    self.models.append({
+                        'name': 'bart-large-mnli',
+                        'pipeline': pipeline(
+                            "zero-shot-classification",
+                            model="facebook/bart-large-mnli",
+                            device=device
+                        ),
+                        'weight': 1.0
+                    })
+                    print("✓ Loaded BART-large-MNLI (fallback)")
+                except Exception as e:
+                    print(f"✗ Failed to load any NLI model: {e}")
+                    raise Exception("No NLI models loaded successfully")
+            
+            # Normalize weights
+            total_weight = sum(m['weight'] for m in self.models)
+            for model in self.models:
+                model['weight'] /= total_weight
+            
+            self._initialized = True
+            print(f"✓ Successfully loaded {len(self.models)} NLI model(s)")
+            
+        except Exception as e:
+            print(f"Error loading NLI models: {e}")
+            self.models = []
+            self._initialized = False
+    
+    def classify(self, claim, evidence):
+        """Classify relationship between claim and evidence using ensemble"""
+        if not self.models:
+            return {
+                'label': 'NEUTRAL',
+                'confidence': 0.5,
+                'model_votes': {}
+            }
+        
+        try:
+            results = []
+            model_votes = {}
+            
+            for model_info in self.models:
+                try:
+                    pipeline_obj = model_info['pipeline']
+                    model_name = model_info['name']
+                    
+                    # Handle different pipeline types
+                    if 'bart' in model_name:
+                        result = pipeline_obj(
+                            evidence,
+                            candidate_labels=["entailment", "contradiction", "neutral"],
+                            hypothesis_template="This example is {}."
+                        )
+                        label = result['labels'][0]
+                        confidence = result['scores'][0]
+                    else:
+                        # Standard NLI: premise [SEP] hypothesis
+                        input_text = f"{evidence} [SEP] {claim}"
+                        result = pipeline_obj(input_text)[0]
+                        label = result['label']
+                        confidence = result['score']
+                    
+                    # Map labels
+                    label_mapping = {
+                        'ENTAILMENT': 'ENTAILMENT',
+                        'CONTRADICTION': 'CONTRADICTION',
+                        'NEUTRAL': 'NEUTRAL',
+                        'entailment': 'ENTAILMENT',
+                        'contradiction': 'CONTRADICTION',
+                        'neutral': 'NEUTRAL',
+                        'LABEL_0': 'CONTRADICTION',
+                        'LABEL_1': 'NEUTRAL',
+                        'LABEL_2': 'ENTAILMENT'
+                    }
+                    
+                    mapped_label = label_mapping.get(label, 'NEUTRAL')
+                    
+                    results.append({
+                        'label': mapped_label,
+                        'confidence': confidence,
+                        'weight': model_info['weight']
+                    })
+                    
+                    model_votes[model_name] = mapped_label
+                    
+                except Exception as e:
+                    print(f"Error with model {model_info['name']}: {e}")
+                    continue
+            
+            if not results:
+                return {
+                    'label': 'NEUTRAL',
+                    'confidence': 0.5,
+                    'model_votes': {}
+                }
+            
+            # Weighted voting
+            weighted_scores = {
+                'ENTAILMENT': 0.0,
+                'CONTRADICTION': 0.0,
+                'NEUTRAL': 0.0
+            }
+            
+            for result in results:
+                weighted_scores[result['label']] += result['confidence'] * result['weight']
+            
+            # Get final label and confidence
+            final_label = max(weighted_scores, key=weighted_scores.get)
+            total_score = sum(weighted_scores.values())
+            final_confidence = weighted_scores[final_label] / total_score if total_score > 0 else 0.5
+            
+            return {
+                'label': final_label,
+                'confidence': final_confidence,
+                'model_votes': model_votes,
+                'weighted_scores': weighted_scores
+            }
+            
+        except Exception as e:
+            print(f"NLI classification error: {e}")
+            return {
+                'label': 'NEUTRAL',
+                'confidence': 0.5,
+                'model_votes': {}
+            }

requirements.txt

@@ -0,0 +1,25 @@
+# requirements.txt - FIXED
+Flask==3.0.0
+Werkzeug==3.0.1
+
+# spaCy with model
+spacy==3.7.5
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl
+
+# Wikipedia and web scraping
+wikipedia==1.4.0
+requests==2.31.0
+beautifulsoup4==4.12.2
+lxml==4.9.3
+
+# NLP and transformers
+sentence-transformers==2.7.0
+transformers==4.36.0
+torch==2.1.0
+torchvision==0.16.0
+tokenizers==0.15.2
+huggingface-hub==0.23.0
+
+# Scientific computing
+scikit-learn==1.3.2
+numpy==1.26.2

run.py

@@ -0,0 +1,17 @@
+# run.py - Entry point to start the application
+
+# Import the create_app function from your app.py
+from app import create_app
+
+# Create the Flask application instance
+app = create_app()
+
+if __name__ == "__main__":
+    print("🚀 Starting TruthCheck System...")
+    print("📊 Flask Backend: http://127.0.0.1:5000") # Updated to 127.0.0.1 for local access
+
+    # Run the Flask application
+    # debug=True enables reloader and debugger, useful during development
+    # host='0.0.0.0' makes the server accessible from other devices on the network
+    # port=5000 is the default Flask port
+    app.run(debug=True, host='0.0.0.0', port=5000)

static/css/style.css

@@ -0,0 +1,72 @@
+/* Custom Scrollbar */
+::-webkit-scrollbar {
+    width: 6px;
+    height: 6px;
+}
+
+::-webkit-scrollbar-track {
+    background: #0f172a; 
+}
+
+::-webkit-scrollbar-thumb {
+    background: #1e293b; 
+    border-radius: 3px;
+}
+
+::-webkit-scrollbar-thumb:hover {
+    background: #0ea5e9; 
+}
+
+/* Base Styles */
+body {
+    -webkit-font-smoothing: antialiased;
+    -moz-osx-font-smoothing: grayscale;
+}
+
+.perspective-1000 {
+    perspective: 1000px;
+}
+
+/* Animations */
+@keyframes fadeInUp {
+    from {
+        opacity: 0;
+        transform: translate3d(0, 20px, 0);
+    }
+    to {
+        opacity: 1;
+        transform: translate3d(0, 0, 0);
+    }
+}
+
+.animate-fade-in-up {
+    animation: fadeInUp 0.8s cubic-bezier(0.2, 0.8, 0.2, 1) forwards;
+}
+
+/* Neon Text utilities */
+.text-neon-cyan {
+    color: #00f3ff;
+    text-shadow: 0 0 5px rgba(0, 243, 255, 0.5), 0 0 10px rgba(0, 243, 255, 0.3);
+}
+
+.text-neon-purple {
+    color: #bc13fe;
+    text-shadow: 0 0 5px rgba(188, 19, 254, 0.5), 0 0 10px rgba(188, 19, 254, 0.3);
+}
+
+/* Markdown Content Styling within Evidence */
+#evidenceList strong {
+    color: #38bdf8;
+    font-weight: 600;
+}
+
+#evidenceList a {
+    color: #0ea5e9;
+    text-decoration: underline;
+    text-decoration-thickness: 1px;
+    text-underline-offset: 2px;
+}
+
+#evidenceList a:hover {
+    color: #00f3ff;
+}

static/js/main.js

@@ -0,0 +1,140 @@
+document.addEventListener('DOMContentLoaded', () => {
+    const claimInput = document.getElementById('claimInput');
+    const verifyBtn = document.getElementById('verifyBtn');
+    const resultSection = document.getElementById('resultSection');
+    const loadingOverlay = document.getElementById('loadingOverlay');
+    const loadingText = document.getElementById('loadingText');
+    const charCount = document.getElementById('charCount');
+
+    // Stats Elements
+    const resultLabel = document.getElementById('resultLabel');
+    const confidenceScore = document.getElementById('confidenceScore');
+    const confidenceCircle = document.getElementById('confidenceCircle');
+    const evidenceList = document.getElementById('evidenceList');
+    const resultBar = document.getElementById('resultBar');
+
+    // Character Count
+    claimInput.addEventListener('input', () => {
+        const len = claimInput.value.length;
+        charCount.textContent = len;
+        if (len > 500) {
+            charCount.classList.add('text-red-500');
+            verifyBtn.disabled = true;
+            verifyBtn.classList.add('opacity-50', 'cursor-not-allowed');
+        } else {
+            charCount.classList.remove('text-red-500');
+            verifyBtn.disabled = false;
+            verifyBtn.classList.remove('opacity-50', 'cursor-not-allowed');
+        }
+    });
+
+    // Verification Logic
+    verifyBtn.addEventListener('click', async () => {
+        const claim = claimInput.value.trim();
+        
+        if (!claim) {
+            alert('Please enter a claim to verify.');
+            return;
+        }
+
+        // Show Loading
+        loadingOverlay.classList.remove('hidden');
+        resultSection.classList.add('hidden');
+        
+        // Animated Loading Text
+        const steps = [
+            "Extracting Facutal Claims...",
+            "Scanning Knowledge Base...",
+            "Retrieving Global Evidence...",
+            "Running NLI Models...",
+            "Calculating Consensus..."
+        ];
+        
+        let stepIndex = 0;
+        const interval = setInterval(() => {
+            if(stepIndex < steps.length) {
+                loadingText.textContent = steps[stepIndex];
+                stepIndex++;
+            }
+        }, 800);
+
+        try {
+            const response = await fetch('/api/verify', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json'
+                },
+                body: JSON.stringify({ claim: claim })
+            });
+
+            clearInterval(interval);
+            const data = await response.json();
+
+            if (data.error) {
+                throw new Error(data.error);
+            }
+
+            // Update UI with results
+            displayResults(data);
+
+        } catch (error) {
+            clearInterval(interval);
+            alert('Error: ' + error.message);
+        } finally {
+            loadingOverlay.classList.add('hidden');
+        }
+    });
+
+    function displayResults(data) {
+        resultSection.classList.remove('hidden');
+        
+        // 1. Label
+        resultLabel.textContent = data.label;
+        
+        // Color coding
+        let colorClass = 'text-gray-400';
+        let barColor = 'bg-gray-400';
+        let strokeColor = 'text-gray-400';
+        
+        if (data.label.toLowerCase() === 'true') {
+            colorClass = 'text-neon-green';
+            barColor = 'bg-green-500';
+            strokeColor = 'text-green-500';
+            resultLabel.style.color = '#4ade80'; // Tailwind green-400
+        } else if (data.label.toLowerCase() === 'false') {
+            colorClass = 'text-neon-red';
+            barColor = 'bg-red-500';
+            strokeColor = 'text-red-500';
+            resultLabel.style.color = '#f87171'; // Tailwind red-400
+        } else {
+            resultLabel.style.color = '#fbbf24'; // Tailwind amber-400
+            barColor = 'bg-amber-400';
+            strokeColor = 'text-amber-400';
+        }
+
+        resultBar.className = `absolute top-0 left-0 w-1 h-full ${barColor}`;
+        confidenceCircle.setAttribute('class', strokeColor);
+
+        // 2. Confidence
+        const percentage = Math.round(data.confidence * 100);
+        confidenceScore.textContent = `${percentage}%`;
+        
+        // Animate Circle
+        // C = 2 * pi * r = 2 * 3.14159 * 28 ≈ 175.9
+        const circumference = 175.9;
+        const offset = circumference - (data.confidence * circumference);
+        confidenceCircle.style.strokeDasharray = `${circumference} ${circumference}`;
+        confidenceCircle.style.strokeDashoffset = offset;
+
+        // 3. Evidence
+        // Format markdown-like evidence summary
+        const formattedEvidence = data.evidence
+            .replace(/\*\*(.*?)\*\*/g, '<strong>$1</strong>')
+            .replace(/\n/g, '<br>');
+        
+        evidenceList.innerHTML = formattedEvidence;
+        
+        // Scroll to results
+        resultSection.scrollIntoView({ behavior: 'smooth', block: 'start' });
+    }
+});

templates/api.html

@@ -0,0 +1,199 @@
+<!DOCTYPE html>
+<html lang="en" class="scroll-smooth">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>API Documentation | TruthCheck</title>
+
+    <!-- Fonts -->
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link
+        href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Orbitron:wght@400;500;600;700;900&family=Fira+Code:wght@400;500&display=swap"
+        rel="stylesheet">
+
+    <!-- Tailwind CSS -->
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script>
+        tailwind.config = {
+            darkMode: 'class',
+            theme: {
+                extend: {
+                    fontFamily: {
+                        sans: ['Inter', 'sans-serif'],
+                        display: ['Orbitron', 'sans-serif'],
+                        mono: ['Fira Code', 'monospace'],
+                    },
+                    colors: {
+                        brand: {
+                            50: '#f0f9ff',
+                            100: '#e0f2fe',
+                            200: '#bae6fd',
+                            300: '#7dd3fc',
+                            400: '#38bdf8',
+                            500: '#0ea5e9',
+                            600: '#0284c7',
+                            700: '#0369a1',
+                            800: '#075985',
+                            900: '#0c4a6e',
+                            950: '#082f49',
+                        },
+                        neon: {
+                            cyan: '#00f3ff',
+                            purple: '#bc13fe',
+                        }
+                    },
+                    animation: {
+                        'pulse-slow': 'pulse 3s cubic-bezier(0.4, 0, 0.6, 1) infinite',
+                        'fade-in-up': 'fadeInUp 0.8s cubic-bezier(0.2, 0.8, 0.2, 1) forwards',
+                    },
+                    keyframes: {
+                        fadeInUp: {
+                            'from': { opacity: '0', transform: 'translate3d(0, 20px, 0)' },
+                            'to': { opacity: '1', transform: 'translate3d(0, 0, 0)' }
+                        }
+                    }
+                }
+            }
+        }
+    </script>
+
+    <!-- Icons -->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+
+    <!-- Custom CSS -->
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+</head>
+
+<body
+    class="bg-slate-950 text-white min-h-screen relative overflow-x-hidden selection:bg-brand-500 selection:text-white">
+
+    <!-- Background Grid Effect -->
+    <div class="fixed inset-0 z-0 opacity-20 pointer-events-none">
+        <div
+            class="absolute inset-0 bg-[linear-gradient(to_right,#4f4f4f2e_1px,transparent_1px),linear-gradient(to_bottom,#4f4f4f2e_1px,transparent_1px)] bg-[size:4rem_4rem] [mask-image:radial-gradient(ellipse_60%_50%_at_50%_0%,#000_70%,transparent_100%)]">
+        </div>
+    </div>
+
+    <!-- Navigation -->
+    <nav class="relative z-50 border-b border-white/10 backdrop-blur-md bg-slate-950/50">
+        <div class="max-w-7xl mx-auto px-4 sm:px-6 lg:px-8">
+            <div class="flex items-center justify-between h-20">
+                <a href="/" class="flex items-center gap-3 group">
+                    <div
+                        class="relative w-10 h-10 flex items-center justify-center bg-brand-500/10 rounded-lg border border-brand-500/50 shadow-[0_0_15px_rgba(14,165,233,0.3)] group-hover:shadow-[0_0_25px_rgba(14,165,233,0.5)] transition-shadow">
+                        <i class="fa-solid fa-shield-halved text-brand-400 text-xl"></i>
+                    </div>
+                    <span
+                        class="font-display font-bold text-2xl tracking-wider text-transparent bg-clip-text bg-gradient-to-r from-white to-slate-400">
+                        TRUTH<span class="text-brand-400">CHECK</span>
+                    </span>
+                </a>
+                <div class="hidden md:flex gap-8">
+                    <a href="/"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">Analyzer</a>
+                    <a href="/how-it-works"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">How it
+                        Works</a>
+                    <a href="/api-docs" class="text-sm font-medium text-brand-400 border-b-2 border-brand-400">API</a>
+                </div>
+            </div>
+        </div>
+    </nav>
+
+    <!-- Main Content -->
+    <main class="relative z-10 container mx-auto px-4 py-16">
+
+        <div class="max-w-4xl mx-auto space-y-12 animate-fade-in-up">
+
+            <!-- Header -->
+            <div class="space-y-4">
+                <h1 class="font-display text-4xl md:text-5xl font-bold text-white">REST API Reference</h1>
+                <p class="text-slate-400 text-lg">Integrate TruthCheck verification directly into your applications.</p>
+            </div>
+
+            <!-- Endpoint Card -->
+            <div class="bg-slate-900/50 border border-white/5 rounded-2xl overflow-hidden">
+                <div class="p-6 border-b border-white/5 bg-slate-900 flex justify-between items-center">
+                    <div class="flex items-center gap-4">
+                        <span
+                            class="px-3 py-1 bg-green-500/20 text-green-400 font-mono text-sm font-bold rounded">POST</span>
+                        <code class="text-lg text-white font-mono">/api/verify</code>
+                    </div>
+                </div>
+
+                <div class="p-8 space-y-8">
+                    <!-- Description -->
+                    <div>
+                        <h3 class="font-display text-lg text-white mb-2">Description</h3>
+                        <p class="text-slate-400">Submit a text claim for verification. The system will process the
+                            claim and return a verdict with supporting evidence.</p>
+                    </div>
+
+                    <!-- Request -->
+                    <div>
+                        <h3 class="font-display text-lg text-white mb-4">Request Body</h3>
+                        <div class="bg-slate-950 p-6 rounded-xl border border-white/10 relative group">
+                            <button class="absolute top-4 right-4 text-slate-500 hover:text-white transition-colors"><i
+                                    class="fa-regular fa-copy"></i></button>
+                            <pre><code class="language-json text-sm font-mono text-brand-300">{
+  "claim": "The Eiffel Tower is located in London"
+}</code></pre>
+                        </div>
+                    </div>
+
+                    <!-- Response -->
+                    <div>
+                        <h3 class="font-display text-lg text-white mb-4">Response</h3>
+                        <div class="bg-slate-950 p-6 rounded-xl border border-white/10 relative group">
+                            <button class="absolute top-4 right-4 text-slate-500 hover:text-white transition-colors"><i
+                                    class="fa-regular fa-copy"></i></button>
+                            <pre><code class="language-json text-sm font-mono text-emerald-300">{
+  "label": "False",
+  "confidence": 0.98,
+  "evidence": "**Analyzed 4 sources**...",
+  "claim": "The Eiffel Tower is located in London"
+}</code></pre>
+                        </div>
+                    </div>
+                </div>
+            </div>
+
+            <!-- Status Codes -->
+            <div class="bg-slate-900/50 border border-white/5 rounded-2xl overflow-hidden p-8">
+                <h3 class="font-display text-lg text-white mb-6">Status Codes</h3>
+                <div class="space-y-4">
+                    <div class="flex gap-4">
+                        <code class="text-green-400 font-mono font-bold w-12">200</code>
+                        <span class="text-slate-300">Successful verification.</span>
+                    </div>
+                    <div class="flex gap-4">
+                        <code class="text-amber-400 font-mono font-bold w-12">400</code>
+                        <span class="text-slate-300">Bad request (missing claim).</span>
+                    </div>
+                    <div class="flex gap-4">
+                        <code class="text-red-400 font-mono font-bold w-12">500</code>
+                        <span class="text-slate-300">Internal server error.</span>
+                    </div>
+                </div>
+            </div>
+
+        </div>
+    </main>
+
+    <!-- Footer -->
+    <footer class="relative z-10 border-t border-white/5 mt-20 bg-slate-950">
+        <div
+            class="max-w-7xl mx-auto px-4 py-8 flex flex-col md:flex-row items-center justify-between text-slate-500 text-sm">
+            <div>&copy; 2025 TruthCheck AI. All Systems Nominal.</div>
+            <div class="flex gap-4 mt-4 md:mt-0">
+                <a href="#" class="hover:text-brand-400 transition-colors">Privacy</a>
+                <a href="#" class="hover:text-brand-400 transition-colors">Terms</a>
+                <a href="https://github.com/CHRISDANIEL145" class="hover:text-brand-400 transition-colors">Github</a>
+            </div>
+        </div>
+    </footer>
+</body>
+
+</html>

templates/dashboard.html

@@ -0,0 +1,284 @@
+<!DOCTYPE html>
+<html lang="en" class="scroll-smooth">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Command Center | TruthCheck</title>
+
+    <!-- Fonts -->
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link
+        href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Orbitron:wght@400;500;600;700;900&display=swap"
+        rel="stylesheet">
+
+    <!-- Tailwind CSS -->
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script>
+        tailwind.config = {
+            darkMode: 'class',
+            theme: {
+                extend: {
+                    fontFamily: {
+                        sans: ['Inter', 'sans-serif'],
+                        display: ['Orbitron', 'sans-serif'],
+                    },
+                    colors: {
+                        brand: {
+                            50: '#f0f9ff',
+                            100: '#e0f2fe',
+                            200: '#bae6fd',
+                            300: '#7dd3fc',
+                            400: '#38bdf8',
+                            500: '#0ea5e9',
+                            600: '#0284c7',
+                            700: '#0369a1',
+                            800: '#075985',
+                            900: '#0c4a6e',
+                            950: '#082f49',
+                        },
+                        neon: {
+                            cyan: '#00f3ff',
+                            purple: '#bc13fe',
+                        }
+                    },
+                    animation: {
+                        'pulse-slow': 'pulse 3s cubic-bezier(0.4, 0, 0.6, 1) infinite',
+                        'fade-in': 'fadeIn 0.5s ease-out forwards',
+                    },
+                    keyframes: {
+                        fadeIn: {
+                            'from': { opacity: '0' },
+                            'to': { opacity: '1' }
+                        }
+                    }
+                }
+            }
+        }
+    </script>
+
+    <!-- Icons -->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+
+    <!-- Custom CSS -->
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+
+    <!-- Chart.js -->
+    <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+</head>
+
+<body
+    class="bg-slate-950 text-white min-h-screen relative overflow-x-hidden selection:bg-brand-500 selection:text-white">
+
+    <!-- Background Grid Effect -->
+    <div class="fixed inset-0 z-0 opacity-20 pointer-events-none">
+        <div
+            class="absolute inset-0 bg-[linear-gradient(to_right,#4f4f4f2e_1px,transparent_1px),linear-gradient(to_bottom,#4f4f4f2e_1px,transparent_1px)] bg-[size:4rem_4rem] [mask-image:radial-gradient(ellipse_60%_50%_at_50%_0%,#000_70%,transparent_100%)]">
+        </div>
+    </div>
+
+    <!-- Navigation -->
+    <nav class="relative z-50 border-b border-white/10 backdrop-blur-md bg-slate-950/50">
+        <div class="max-w-7xl mx-auto px-4 sm:px-6 lg:px-8">
+            <div class="flex items-center justify-between h-20">
+                <a href="/" class="flex items-center gap-3 group">
+                    <div
+                        class="relative w-10 h-10 flex items-center justify-center bg-brand-500/10 rounded-lg border border-brand-500/50 shadow-[0_0_15px_rgba(14,165,233,0.3)] group-hover:shadow-[0_0_25px_rgba(14,165,233,0.5)] transition-shadow">
+                        <i class="fa-solid fa-shield-halved text-brand-400 text-xl"></i>
+                    </div>
+                    <span
+                        class="font-display font-bold text-2xl tracking-wider text-transparent bg-clip-text bg-gradient-to-r from-white to-slate-400">
+                        TRUTH<span class="text-brand-400">CHECK</span>
+                    </span>
+                </a>
+                <div class="hidden md:flex gap-8">
+                    <a href="/"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">Analyzer</a>
+                    <a href="#" class="text-sm font-medium text-brand-400 border-b-2 border-brand-400">Dashboard</a>
+                    <a href="/how-it-works"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">How it
+                        Works</a>
+                    <a href="/api-docs"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">API</a>
+                </div>
+            </div>
+        </div>
+    </nav>
+
+    <!-- Main Content -->
+    <main class="relative z-10 container mx-auto px-4 py-8">
+
+        <!-- Header -->
+        <div class="flex justify-between items-end mb-8 animate-fade-in">
+            <div>
+                <h1 class="font-display text-3xl md:text-4xl font-bold text-white mb-2">Command Center</h1>
+                <p class="text-slate-400">Global verification telemetry and history.</p>
+            </div>
+            <button onclick="loadHistory()"
+                class="bg-slate-800 hover:bg-slate-700 text-white px-4 py-2 rounded-lg text-sm font-medium transition-colors border border-white/5">
+                <i class="fa-solid fa-rotate-right mr-2"></i> Refresh
+            </button>
+        </div>
+
+        <!-- Stats Grid -->
+        <div class="grid grid-cols-1 md:grid-cols-4 gap-6 mb-12 animate-fade-in" style="animation-delay: 0.1s;">
+            <!-- Stat 1 -->
+            <div class="bg-slate-900/50 border border-white/5 p-6 rounded-xl backdrop-blur-sm">
+                <div class="flex items-start justify-between">
+                    <div>
+                        <div class="text-slate-400 text-sm font-medium mb-1">Total Scans</div>
+                        <div class="text-3xl font-display font-bold text-white" id="statTotal">0</div>
+                    </div>
+                    <div class="bg-brand-500/10 p-3 rounded-lg text-brand-400">
+                        <i class="fa-solid fa-chart-line"></i>
+                    </div>
+                </div>
+            </div>
+            <!-- Stat 2 -->
+            <div class="bg-slate-900/50 border border-white/5 p-6 rounded-xl backdrop-blur-sm">
+                <div class="flex items-start justify-between">
+                    <div>
+                        <div class="text-slate-400 text-sm font-medium mb-1">Truth Rate</div>
+                        <div class="text-3xl font-display font-bold text-white" id="statTrueRate">0%</div>
+                    </div>
+                    <div class="bg-green-500/10 p-3 rounded-lg text-green-400">
+                        <i class="fa-solid fa-check"></i>
+                    </div>
+                </div>
+            </div>
+            <!-- Stat 3 -->
+            <div class="bg-slate-900/50 border border-white/5 p-6 rounded-xl backdrop-blur-sm">
+                <div class="flex items-start justify-between">
+                    <div>
+                        <div class="text-slate-400 text-sm font-medium mb-1">Misinfo Detected</div>
+                        <div class="text-3xl font-display font-bold text-white" id="statFalseRate">0%</div>
+                    </div>
+                    <div class="bg-red-500/10 p-3 rounded-lg text-red-400">
+                        <i class="fa-solid fa-triangle-exclamation"></i>
+                    </div>
+                </div>
+            </div>
+            <!-- Stat 4 -->
+            <div class="bg-slate-900/50 border border-white/5 p-6 rounded-xl backdrop-blur-sm">
+                <div class="flex items-start justify-between">
+                    <div>
+                        <div class="text-slate-400 text-sm font-medium mb-1">Avg Confidence</div>
+                        <div class="text-3xl font-display font-bold text-white" id="statAvgConf">0%</div>
+                    </div>
+                    <div class="bg-neon-purple/10 p-3 rounded-lg text-neon-purple">
+                        <i class="fa-solid fa-bullseye"></i>
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <!-- History Table -->
+        <div class="bg-slate-900/50 border border-white/5 rounded-2xl overflow-hidden backdrop-blur-sm animate-fade-in"
+            style="animation-delay: 0.2s;">
+            <div class="p-6 border-b border-white/5">
+                <h3 class="font-display text-xl font-bold text-white">Recent Verifications</h3>
+            </div>
+
+            <div class="overflow-x-auto">
+                <table class="w-full text-left">
+                    <thead class="bg-slate-950/50 text-slate-400 uppercase text-xs font-medium">
+                        <tr>
+                            <th class="px-6 py-4">Status</th>
+                            <th class="px-6 py-4">Claim</th>
+                            <th class="px-6 py-4">Confidence</th>
+                            <th class="px-6 py-4">Timestamp</th>
+                        </tr>
+                    </thead>
+                    <tbody class="divide-y divide-white/5 text-sm" id="historyTableBody">
+                        <!-- Rows injected via JS -->
+                    </tbody>
+                </table>
+            </div>
+
+            <div id="emptyState" class="hidden p-12 text-center text-slate-500">
+                <i class="fa-solid fa-inbox text-4xl mb-4 opacity-50"></i>
+                <p>No verification history found.</p>
+            </div>
+        </div>
+
+    </main>
+
+    <script>
+        document.addEventListener('DOMContentLoaded', loadHistory);
+
+        async function loadHistory() {
+            try {
+                const response = await fetch('/api/history');
+                const data = await response.json();
+
+                updateStats(data);
+                renderTable(data);
+            } catch (error) {
+                console.error("Failed to load history:", error);
+            }
+        }
+
+        function updateStats(data) {
+            if (!data.length) return;
+
+            const total = data.length;
+            const trueCount = data.filter(i => i.label.toLowerCase() === 'true').length;
+            const falseCount = data.filter(i => i.label.toLowerCase() === 'false').length;
+
+            const totalConfidence = data.reduce((acc, curr) => acc + curr.confidence, 0);
+            const avgConf = total > 0 ? (totalConfidence / total) : 0;
+
+            document.getElementById('statTotal').textContent = total;
+            document.getElementById('statTrueRate').textContent = Math.round((trueCount / total) * 100) + '%';
+            document.getElementById('statFalseRate').textContent = Math.round((falseCount / total) * 100) + '%';
+            document.getElementById('statAvgConf').textContent = Math.round(avgConf * 100) + '%';
+        }
+
+        function renderTable(data) {
+            const tbody = document.getElementById('historyTableBody');
+            const emptyState = document.getElementById('emptyState');
+            tbody.innerHTML = '';
+
+            if (data.length === 0) {
+                emptyState.classList.remove('hidden');
+                return;
+            } else {
+                emptyState.classList.add('hidden');
+            }
+
+            data.forEach(row => {
+                const tr = document.createElement('tr');
+                tr.className = 'hover:bg-white/5 transition-colors';
+
+                // Status Badge
+                let statusBadge = '';
+                if (row.label.toLowerCase() === 'true') {
+                    statusBadge = '<span class="inline-flex items-center gap-1.5 px-2.5 py-1 rounded-full text-xs font-medium bg-green-500/10 text-green-400 border border-green-500/20"><i class="fa-solid fa-check"></i> TRUE</span>';
+                } else if (row.label.toLowerCase() === 'false') {
+                    statusBadge = '<span class="inline-flex items-center gap-1.5 px-2.5 py-1 rounded-full text-xs font-medium bg-red-500/10 text-red-400 border border-red-500/20"><i class="fa-solid fa-xmark"></i> FALSE</span>';
+                } else {
+                    statusBadge = '<span class="inline-flex items-center gap-1.5 px-2.5 py-1 rounded-full text-xs font-medium bg-amber-500/10 text-amber-400 border border-amber-500/20"><i class="fa-solid fa-question"></i> LOW CONF</span>';
+                }
+
+                // Date
+                const date = new Date(row.date).toLocaleString();
+
+                tr.innerHTML = `
+                    <td class="px-6 py-4 whitespace-nowrap">${statusBadge}</td>
+                    <td class="px-6 py-4 text-slate-300 font-light truncate max-w-md" title="${row.claim}">${row.claim}</td>
+                    <td class="px-6 py-4 text-slate-400 flex items-center gap-2">
+                        <div class="w-16 h-1.5 bg-slate-800 rounded-full overflow-hidden">
+                            <div class="h-full bg-brand-500" style="width: ${row.confidence * 100}%"></div>
+                        </div>
+                        ${Math.round(row.confidence * 100)}%
+                    </td>
+                    <td class="px-6 py-4 text-slate-500 font-mono text-xs">${date}</td>
+                `;
+                tbody.appendChild(tr);
+            });
+        }
+    </script>
+</body>
+
+</html>

templates/how_it_works.html

@@ -0,0 +1,216 @@
+<!DOCTYPE html>
+<html lang="en" class="scroll-smooth">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>How it Works | TruthCheck</title>
+
+    <!-- Fonts -->
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link
+        href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Orbitron:wght@400;500;600;700;900&display=swap"
+        rel="stylesheet">
+
+    <!-- Tailwind CSS -->
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script>
+        tailwind.config = {
+            darkMode: 'class',
+            theme: {
+                extend: {
+                    fontFamily: {
+                        sans: ['Inter', 'sans-serif'],
+                        display: ['Orbitron', 'sans-serif'],
+                    },
+                    colors: {
+                        brand: {
+                            50: '#f0f9ff',
+                            100: '#e0f2fe',
+                            200: '#bae6fd',
+                            300: '#7dd3fc',
+                            400: '#38bdf8',
+                            500: '#0ea5e9',
+                            600: '#0284c7',
+                            700: '#0369a1',
+                            800: '#075985',
+                            900: '#0c4a6e',
+                            950: '#082f49',
+                        },
+                        neon: {
+                            cyan: '#00f3ff',
+                            purple: '#bc13fe',
+                        }
+                    },
+                    animation: {
+                        'pulse-slow': 'pulse 3s cubic-bezier(0.4, 0, 0.6, 1) infinite',
+                        'fade-in-up': 'fadeInUp 0.8s cubic-bezier(0.2, 0.8, 0.2, 1) forwards',
+                    },
+                    keyframes: {
+                        fadeInUp: {
+                            'from': { opacity: '0', transform: 'translate3d(0, 20px, 0)' },
+                            'to': { opacity: '1', transform: 'translate3d(0, 0, 0)' }
+                        }
+                    }
+                }
+            }
+        }
+    </script>
+
+    <!-- Icons -->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+
+    <!-- Custom CSS -->
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+</head>
+
+<body
+    class="bg-slate-950 text-white min-h-screen relative overflow-x-hidden selection:bg-brand-500 selection:text-white">
+
+    <!-- Background Grid Effect -->
+    <div class="fixed inset-0 z-0 opacity-20 pointer-events-none">
+        <div
+            class="absolute inset-0 bg-[linear-gradient(to_right,#4f4f4f2e_1px,transparent_1px),linear-gradient(to_bottom,#4f4f4f2e_1px,transparent_1px)] bg-[size:4rem_4rem] [mask-image:radial-gradient(ellipse_60%_50%_at_50%_0%,#000_70%,transparent_100%)]">
+        </div>
+    </div>
+
+    <!-- Navigation -->
+    <nav class="relative z-50 border-b border-white/10 backdrop-blur-md bg-slate-950/50">
+        <div class="max-w-7xl mx-auto px-4 sm:px-6 lg:px-8">
+            <div class="flex items-center justify-between h-20">
+                <a href="/" class="flex items-center gap-3 group">
+                    <div
+                        class="relative w-10 h-10 flex items-center justify-center bg-brand-500/10 rounded-lg border border-brand-500/50 shadow-[0_0_15px_rgba(14,165,233,0.3)] group-hover:shadow-[0_0_25px_rgba(14,165,233,0.5)] transition-shadow">
+                        <i class="fa-solid fa-shield-halved text-brand-400 text-xl"></i>
+                    </div>
+                    <span
+                        class="font-display font-bold text-2xl tracking-wider text-transparent bg-clip-text bg-gradient-to-r from-white to-slate-400">
+                        TRUTH<span class="text-brand-400">CHECK</span>
+                    </span>
+                </a>
+                <div class="hidden md:flex gap-8">
+                    <a href="/"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">Analyzer</a>
+                    <a href="/dashboard"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">Dashboard</a>
+                    <a href="/how-it-works" class="text-sm font-medium text-brand-400 border-b-2 border-brand-400">How
+                        it Works</a>
+                    <a href="/api-docs"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">API</a>
+                </div>
+            </div>
+        </div>
+    </nav>
+
+    <!-- Main Content -->
+    <main class="relative z-10 container mx-auto px-4 py-16">
+
+        <div class="max-w-4xl mx-auto space-y-16 animate-fade-in-up">
+
+            <!-- Header -->
+            <div class="text-center space-y-4">
+                <h1 class="font-display text-4xl md:text-5xl font-bold text-white">System Architecture</h1>
+                <p class="text-slate-400 text-lg">Declassified overview of the TruthCheck verification pipeline.</p>
+            </div>
+
+            <!-- Steps -->
+            <div class="space-y-12">
+                <!-- Step 1 -->
+                <div
+                    class="flex flex-col md:flex-row gap-8 items-center bg-slate-900/50 border border-white/5 p-8 rounded-2xl hover:border-brand-500/30 transition-colors">
+                    <div
+                        class="flex-shrink-0 w-16 h-16 rounded-full bg-brand-500/10 border border-brand-500/30 flex items-center justify-center text-2xl font-display font-bold text-brand-400">
+                        01
+                    </div>
+                    <div>
+                        <h3 class="font-display text-2xl font-bold text-white mb-2">Claim Extraction</h3>
+                        <p class="text-slate-400 leading-relaxed">
+                            The system first analyzes your input text using <strong>spaCy</strong> to identify factual
+                            claims. It filters out questions, opinions, and personal statements, isolating only
+                            verifiable assertions about the real world.
+                        </p>
+                    </div>
+                </div>
+
+                <!-- Step 2 -->
+                <div
+                    class="flex flex-col md:flex-row gap-8 items-center bg-slate-900/50 border border-white/5 p-8 rounded-2xl hover:border-neon-cyan/30 transition-colors">
+                    <div
+                        class="flex-shrink-0 w-16 h-16 rounded-full bg-neon-cyan/10 border border-neon-cyan/30 flex items-center justify-center text-2xl font-display font-bold text-neon-cyan">
+                        02
+                    </div>
+                    <div>
+                        <h3 class="font-display text-2xl font-bold text-white mb-2">Evidence Retrieval</h3>
+                        <p class="text-slate-400 leading-relaxed">
+                            Using extracted keywords, TruthCheck scrapes trusted sources (Wikipedia, Government domains,
+                            Scientific Journals) via standard search protocols. It specifically prioritizes
+                            high-credibility domains like <code>.gov</code>, <code>.edu</code>, and
+                            <code>reuters.com</code>.
+                        </p>
+                    </div>
+                </div>
+
+                <!-- Step 3 -->
+                <div
+                    class="flex flex-col md:flex-row gap-8 items-center bg-slate-900/50 border border-white/5 p-8 rounded-2xl hover:border-neon-purple/30 transition-colors">
+                    <div
+                        class="flex-shrink-0 w-16 h-16 rounded-full bg-neon-purple/10 border border-neon-purple/30 flex items-center justify-center text-2xl font-display font-bold text-neon-purple">
+                        03
+                    </div>
+                    <div>
+                        <h3 class="font-display text-2xl font-bold text-white mb-2">NLI Classification</h3>
+                        <p class="text-slate-400 leading-relaxed">
+                            The core "brain" uses Large Language Models (RoBERTa & DeBERTa) fine-tuned for
+                            <strong>Natural Language Inference (NLI)</strong>. It compares the claim against each piece
+                            of evidence to determine if the evidence <em>Entails</em> (supports), <em>Contradicts</em>
+                            (refutes), or is <em>Neutral</em> towards the claim.
+                        </p>
+                    </div>
+                </div>
+
+                <!-- Step 4 -->
+                <div
+                    class="flex flex-col md:flex-row gap-8 items-center bg-slate-900/50 border border-white/5 p-8 rounded-2xl hover:border-green-500/30 transition-colors">
+                    <div
+                        class="flex-shrink-0 w-16 h-16 rounded-full bg-green-500/10 border border-green-500/30 flex items-center justify-center text-2xl font-display font-bold text-green-500">
+                        04
+                    </div>
+                    <div>
+                        <h3 class="font-display text-2xl font-bold text-white mb-2">Consensus Voting</h3>
+                        <p class="text-slate-400 leading-relaxed">
+                            Finally, all model judgments are aggregated using a weighted voting mechanism. Sources with
+                            higher domain authority carry more weight. The system calculates a final confidence score
+                            and issues a verdict: <strong>TRUE</strong>, <strong>FALSE</strong>, or <strong>LOW
+                                CONFIDENCE</strong>.
+                        </p>
+                    </div>
+                </div>
+            </div>
+
+            <!-- CTA -->
+            <div class="text-center pt-8">
+                <a href="/"
+                    class="inline-flex items-center gap-2 px-8 py-3 bg-brand-600 hover:bg-brand-500 text-white rounded-full font-bold font-display transition-all shadow-[0_0_20px_rgba(14,165,233,0.3)] hover:shadow-[0_0_30px_rgba(14,165,233,0.5)]">
+                    <i class="fa-solid fa-play"></i> Try the Analyzer
+                </a>
+            </div>
+
+        </div>
+    </main>
+
+    <!-- Footer -->
+    <footer class="relative z-10 border-t border-white/5 mt-20 bg-slate-950">
+        <div
+            class="max-w-7xl mx-auto px-4 py-8 flex flex-col md:flex-row items-center justify-between text-slate-500 text-sm">
+            <div>&copy; 2025 TruthCheck AI. All Systems Nominal.</div>
+            <div class="flex gap-4 mt-4 md:mt-0">
+                <a href="#" class="hover:text-brand-400 transition-colors">Privacy</a>
+                <a href="#" class="hover:text-brand-400 transition-colors">Terms</a>
+                <a href="https://github.com/CHRISDANIEL145" class="hover:text-brand-400 transition-colors">Github</a>
+            </div>
+        </div>
+    </footer>
+</body>
+
+</html>

templates/index.html

@@ -0,0 +1,282 @@
+<!DOCTYPE html>
+<html lang="en" class="scroll-smooth">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>TruthCheck | AI-Powered Fact Verification</title>
+
+    <!-- Fonts -->
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link
+        href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Orbitron:wght@400;500;600;700;900&display=swap"
+        rel="stylesheet">
+
+    <!-- Tailwind CSS -->
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script>
+        tailwind.config = {
+            darkMode: 'class',
+            theme: {
+                extend: {
+                    fontFamily: {
+                        sans: ['Inter', 'sans-serif'],
+                        display: ['Orbitron', 'sans-serif'],
+                    },
+                    colors: {
+                        brand: {
+                            50: '#f0f9ff',
+                            100: '#e0f2fe',
+                            200: '#bae6fd',
+                            300: '#7dd3fc',
+                            400: '#38bdf8',
+                            500: '#0ea5e9', // Sky Blue
+                            600: '#0284c7',
+                            700: '#0369a1',
+                            800: '#075985',
+                            900: '#0c4a6e',
+                            950: '#082f49',
+                        },
+                        neon: {
+                            cyan: '#00f3ff',
+                            purple: '#bc13fe',
+                            green: '#0aff0a',
+                            red: '#ff0a0a'
+                        }
+                    },
+                    animation: {
+                        'pulse-slow': 'pulse 3s cubic-bezier(0.4, 0, 0.6, 1) infinite',
+                        'glow': 'glow 2s ease-in-out infinite alternate',
+                        'scan': 'scan 2s linear infinite',
+                    },
+                    keyframes: {
+                        glow: {
+                            '0%': { boxShadow: '0 0 5px #00f3ff, 0 0 10px #00f3ff' },
+                            '100%': { boxShadow: '0 0 20px #00f3ff, 0 0 40px #00f3ff' }
+                        },
+                        scan: {
+                            '0%': { transform: 'translateY(-100%)' },
+                            '100%': { transform: 'translateY(100%)' }
+                        }
+                    }
+                }
+            }
+        }
+    </script>
+
+    <!-- Icons -->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+
+    <!-- Custom CSS -->
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+</head>
+
+<body
+    class="bg-slate-950 text-white min-h-screen relative overflow-x-hidden selection:bg-brand-500 selection:text-white">
+
+    <!-- Background Grid Effect -->
+    <div class="fixed inset-0 z-0 opacity-20 pointer-events-none">
+        <div
+            class="absolute inset-0 bg-[linear-gradient(to_right,#4f4f4f2e_1px,transparent_1px),linear-gradient(to_bottom,#4f4f4f2e_1px,transparent_1px)] bg-[size:4rem_4rem] [mask-image:radial-gradient(ellipse_60%_50%_at_50%_0%,#000_70%,transparent_100%)]">
+        </div>
+    </div>
+
+    <!-- Glowing Orbs -->
+    <div
+        class="fixed top-0 left-1/4 w-96 h-96 bg-brand-500/20 rounded-full blur-[128px] pointer-events-none animate-pulse-slow">
+    </div>
+    <div class="fixed bottom-0 right-1/4 w-96 h-96 bg-neon-purple/20 rounded-full blur-[128px] pointer-events-none animate-pulse-slow"
+        style="animation-delay: 1.5s;"></div>
+
+    <!-- Navigation -->
+    <nav class="relative z-50 border-b border-white/10 backdrop-blur-md bg-slate-950/50">
+        <div class="max-w-7xl mx-auto px-4 sm:px-6 lg:px-8">
+            <div class="flex items-center justify-between h-20">
+                <div class="flex items-center gap-3">
+                    <div
+                        class="relative w-10 h-10 flex items-center justify-center bg-brand-500/10 rounded-lg border border-brand-500/50 shadow-[0_0_15px_rgba(14,165,233,0.3)]">
+                        <i class="fa-solid fa-shield-halved text-brand-400 text-xl"></i>
+                    </div>
+                    <span
+                        class="font-display font-bold text-2xl tracking-wider text-transparent bg-clip-text bg-gradient-to-r from-white to-slate-400">
+                        TRUTH<span class="text-brand-400">CHECK</span>
+                    </span>
+                </div>
+                <div class="hidden md:flex gap-8">
+                    <a href="/" class="text-sm font-medium text-brand-400 border-b-2 border-brand-400">Analyzer</a>
+                    <a href="/dashboard"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">Dashboard</a>
+                    <a href="/how-it-works"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">How it
+                        Works</a>
+                    <a href="/api-docs"
+                        class="text-sm font-medium text-slate-300 hover:text-brand-400 transition-colors">API</a>
+                </div>
+                <button
+                    class="bg-brand-600 hover:bg-brand-500 text-white px-6 py-2 rounded-full font-medium text-sm transition-all shadow-[0_0_20px_rgba(14,165,233,0.3)] hover:shadow-[0_0_30px_rgba(14,165,233,0.5)] border border-brand-400/50">
+                    Connect
+                </button>
+            </div>
+        </div>
+    </nav>
+
+    <!-- Main Content -->
+    <main class="relative z-10 container mx-auto px-4 py-16 flex flex-col items-center">
+
+        <!-- Hero Section -->
+        <div class="text-center max-w-4xl mx-auto mb-16 space-y-6 animate-fade-in-up">
+            <div
+                class="inline-flex items-center gap-2 px-4 py-2 rounded-full bg-brand-500/10 border border-brand-500/20 text-brand-300 text-sm font-medium mb-4">
+                <span class="relative flex h-2 w-2">
+                    <span
+                        class="animate-ping absolute inline-flex h-full w-full rounded-full bg-brand-400 opacity-75"></span>
+                    <span class="relative inline-flex rounded-full h-2 w-2 bg-brand-500"></span>
+                </span>
+                AI-Powered Verification Engine V2.0
+            </div>
+
+            <h1 class="font-display text-5xl md:text-7xl font-bold leading-tight">
+                Verify Reality in <br>
+                <span
+                    class="text-transparent bg-clip-text bg-gradient-to-r from-brand-400 via-neon-cyan to-brand-500 drop-shadow-[0_0_15px_rgba(14,165,233,0.5)]">
+                    Real-Time
+                </span>
+            </h1>
+
+            <p class="text-slate-400 text-lg md:text-xl max-w-2xl mx-auto font-light">
+                Analyze any text statement using our advanced neural network ensemble.
+                Detect misinformation with military-grade precision.
+            </p>
+        </div>
+
+        <!-- Verification Interface -->
+        <div class="w-full max-w-3xl relative group perspective-1000">
+            <!-- Glass Card -->
+            <div
+                class="relative bg-slate-900/60 backdrop-blur-xl border border-white/10 rounded-2xl p-1 shadow-2xl transition-all duration-300 hover:border-brand-500/30 hover:shadow-[0_0_50px_rgba(14,165,233,0.1)]">
+
+                <div class="p-6 md:p-8 space-y-6">
+                    <!-- Input Area -->
+                    <div class="relative">
+                        <textarea id="claimInput" rows="4"
+                            class="w-full bg-slate-950/80 border border-slate-700/50 rounded-xl p-5 text-lg text-slate-200 placeholder-slate-600 focus:outline-none focus:border-brand-500/50 focus:ring-1 focus:ring-brand-500/50 transition-all resize-none font-light tracking-wide"
+                            placeholder="Enter a statement to verify... (e.g., 'The Eiffel Tower is located in London')"></textarea>
+
+                        <div class="absolute bottom-4 right-4 text-xs text-slate-500 font-mono">
+                            <span id="charCount">0</span>/500
+                        </div>
+                    </div>
+
+                    <!-- Action Bar -->
+                    <div class="flex items-center justify-between">
+                        <div class="flex gap-4 text-sm text-slate-400">
+                            <label
+                                class="flex items-center gap-2 cursor-pointer hover:text-brand-300 transition-colors">
+                                <input type="checkbox" checked
+                                    class="accent-brand-500 bg-slate-800 border-slate-600 rounded">
+                                <span>Deep Search</span>
+                            </label>
+                            <label
+                                class="flex items-center gap-2 cursor-pointer hover:text-brand-300 transition-colors">
+                                <input type="checkbox" checked
+                                    class="accent-brand-500 bg-slate-800 border-slate-600 rounded">
+                                <span>Multi-Model Consensus</span>
+                            </label>
+                        </div>
+
+                        <button id="verifyBtn"
+                            class="group relative px-8 py-3 bg-white text-slate-950 rounded-xl font-bold font-display hover:bg-brand-50 text-base transition-all overflow-hidden">
+                            <span class="relative z-10 flex items-center gap-2">
+                                INIT_SCAN <i
+                                    class="fa-solid fa-arrow-right group-hover:translate-x-1 transition-transform"></i>
+                            </span>
+                            <div
+                                class="absolute inset-0 bg-gradient-to-r from-brand-400 to-neon-cyan opacity-0 group-hover:opacity-20 transition-opacity">
+                            </div>
+                        </button>
+                    </div>
+                </div>
+
+                <!-- Loading Overlay -->
+                <div id="loadingOverlay"
+                    class="absolute inset-0 bg-slate-950/90 backdrop-blur-sm rounded-2xl flex flex-col items-center justify-center z-20 hidden">
+                    <div class="relative w-24 h-24 mb-6">
+                        <div class="absolute inset-0 border-4 border-slate-800 rounded-full"></div>
+                        <div class="absolute inset-0 border-t-4 border-brand-500 rounded-full animate-spin"></div>
+                        <div class="absolute inset-4 bg-brand-500/20 rounded-full blur-md animate-pulse"></div>
+                        <i
+                            class="fa-solid fa-fingerprint absolute inset-0 flex items-center justify-center text-brand-400 text-3xl opacity-80"></i>
+                    </div>
+                    <div class="font-display text-xl font-bold text-white tracking-widest animate-pulse">ANALYZING</div>
+                    <div class="text-brand-400 font-mono text-sm mt-2" id="loadingText">Connecting to neural core...
+                    </div>
+                </div>
+            </div>
+
+            <!-- Result Section -->
+            <div id="resultSection" class="mt-8 hidden space-y-6">
+
+                <!-- Main Label Card -->
+                <div
+                    class="bg-slate-900/80 border border-white/10 rounded-2xl p-8 backdrop-blur-md relative overflow-hidden">
+                    <div class="absolute top-0 left-0 w-1 h-full bg-gray-600" id="resultBar"></div>
+
+                    <div class="flex flex-col md:flex-row items-start md:items-center justify-between gap-6">
+                        <div>
+                            <div class="text-slate-400 text-sm font-mono mb-1 uppercase tracking-wider">Verdict Analysis
+                            </div>
+                            <h2 id="resultLabel" class="font-display text-4xl font-bold text-white">--</h2>
+                        </div>
+
+                        <div class="flex items-center gap-6">
+                            <div class="text-right">
+                                <div class="text-3xl font-bold font-display text-white" id="confidenceScore">0%</div>
+                                <div class="text-slate-400 text-xs uppercase">Confidence</div>
+                            </div>
+                            <div class="w-16 h-16 relative flex items-center justify-center">
+                                <svg class="w-full h-full transform -rotate-90">
+                                    <circle cx="32" cy="32" r="28" stroke="currentColor" stroke-width="4"
+                                        fill="transparent" class="text-slate-800" />
+                                    <circle id="confidenceCircle" cx="32" cy="32" r="28" stroke="currentColor"
+                                        stroke-width="4" fill="transparent" class="text-brand-500"
+                                        stroke-dasharray="175.9" stroke-dashoffset="175.9" />
+                                </svg>
+                            </div>
+                        </div>
+                    </div>
+                </div>
+
+                <!-- Evidence Section -->
+                <div class="bg-slate-900/50 border border-white/5 rounded-2xl p-6 backdrop-blur-md">
+                    <h3 class="font-display text-lg font-bold text-white mb-4 flex items-center gap-2">
+                        <i class="fa-solid fa-list-check text-brand-400"></i> Evidence Stream
+                    </h3>
+                    <div id="evidenceList"
+                        class="space-y-4 max-h-[500px] overflow-y-auto pr-2 custom-scrollbar text-slate-300 font-light leading-relaxed">
+                        <!-- Evidence items injected here -->
+                    </div>
+                </div>
+
+            </div>
+        </div>
+
+    </main>
+
+    <!-- Footer -->
+    <footer class="relative z-10 border-t border-white/5 mt-20 bg-slate-950">
+        <div
+            class="max-w-7xl mx-auto px-4 py-8 flex flex-col md:flex-row items-center justify-between text-slate-500 text-sm">
+            <div>&copy; 2025 TruthCheck AI. All Systems Nominal.</div>
+            <div class="flex gap-4 mt-4 md:mt-0">
+                <a href="#" class="hover:text-brand-400 transition-colors">Privacy</a>
+                <a href="#" class="hover:text-brand-400 transition-colors">Terms</a>
+                <a href="#" class="hover:text-brand-400 transition-colors">Github</a>
+            </div>
+        </div>
+    </footer>
+
+    <script src="{{ url_for('static', filename='js/main.js') }}"></script>
+</body>
+
+</html>

utils/__init__.py

@@ -0,0 +1,3 @@
+"""
+TruthCheck Utilities Package
+"""

utils/config.py

@@ -0,0 +1,22 @@
+# utils/config.py
+import os
+
+class Config:
+    """Enhanced configuration for TruthCheck"""
+    
+    # Model settings
+    SIMILARITY_THRESHOLD = 0.45  # Lowered slightly for better recall
+    CONFIDENCE_THRESHOLD = 0.6   # Consensus threshold
+    CONSENSUS_THRESHOLD = 0.6    # For multi-evidence voting
+    
+    # Evidence settings
+    MAX_EVIDENCE_SOURCES = 10
+    TOP_EVIDENCE_FOR_NLI = 4  # Use top 4 for consensus
+    
+    # Flask settings
+    SECRET_KEY = os.environ.get('SECRET_KEY', 'truthcheck-production-key-2025')
+    DEBUG = os.environ.get('DEBUG', 'False').lower() == 'true'
+    
+    # Model paths
+    SPACY_MODEL = "en_core_web_sm"
+    SBERT_MODEL = "all-MiniLM-L6-v2"

utils/similarity.py

@@ -0,0 +1,43 @@
+# utils/similarity.py
+from sentence_transformers import SentenceTransformer
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+
+class SimilarityCalculator:
+    def __init__(self): # Corrected __init__
+        """Initialize sentence transformer model"""
+        try:
+            self.model = SentenceTransformer('all-MiniLM-L6-v2')
+        except Exception as e:
+            print(f"Error loading similarity model: {e}")
+            self.model = None
+    
+    def calculate_similarity(self, text1, text2):
+        """Calculate semantic similarity between two texts"""
+        if not self.model:
+            print("Similarity model not loaded. Returning fallback similarity.")
+            return 0.5  # Fallback similarity
+        
+        try:
+            # Encode texts to embeddings
+            embeddings = self.model.encode([text1, text2])
+            
+            # Calculate cosine similarity
+            similarity = cosine_similarity(
+                embeddings[0].reshape(1, -1),
+                embeddings[1].reshape(1, -1)
+            )[0][0]
+            
+            return float(similarity)
+            
+        except Exception as e:
+            print(f"Similarity calculation error: {e}")
+            return 0.5
+
+# Global similarity calculator instance
+_similarity_calculator = SimilarityCalculator()
+
+def calculate_similarity(text1, text2):
+    """Global function to calculate similarity"""
+    return _similarity_calculator.calculate_similarity(text1, text2)
+