Upload folder using huggingface_hub

app.py

@@ -118,7 +118,6 @@ def collect_clock_jitter(n=256):
     for _ in range(n * 4):
         timestamps.append(time.perf_counter_ns())
     deltas = np.diff(timestamps).astype(np.float64)
-    # Subsample
     block = len(deltas) // n
     signal = np.array([deltas[i*block:(i+1)*block].mean() for i in range(n)])
     return (signal - signal.mean()) / (signal.std() + 1e-15)
@@ -152,7 +151,7 @@ def run_oracle_prediction(question: str, deadline: str, n_samples: int = 256, n_
     q_hash = hashlib.sha256(question.encode()).hexdigest()
     base_seed = int(q_hash[:8], 16)
     
-    # Collect signals from 4 sources (simplified for demo)
+    # Collect signals from 4 sources
     sources = {
         "entropy": collect_entropy(n_samples, seed=base_seed),
         "clock": collect_clock_jitter(n_samples),
@@ -185,10 +184,12 @@ def run_oracle_prediction(question: str, deadline: str, n_samples: int = 256, n_
     # Confidence
     mean_z = np.mean(z_scores)
     if mean_z >= 10:
+        confidence = "VERY HIGH"
+    elif mean_z >= 5:
         confidence = "HIGH"
     elif mean_z >= 3:
         confidence = "MEDIUM"
-    elif mean_z >= 1:
+    elif mean_z >= 1.5:
         confidence = "LOW"
     else:
         confidence = "UNCERTAIN"
@@ -198,81 +199,234 @@ def run_oracle_prediction(question: str, deadline: str, n_samples: int = 256, n_
     prob = 1.0 / (1.0 + np.exp(-k * mean_z))
     prob = max(0.5, min(prob, 0.95))
     
-    return results, consensus, confidence, prob, vote_count
+    return results, consensus, confidence, prob, vote_count, mean_z
 
 
-def format_results(question, deadline, results, consensus, confidence, prob, votes):
-    """Format results as markdown."""
+def create_source_chart(results):
+    """Create a visual bar chart of z-scores."""
+    import matplotlib
+    matplotlib.use('Agg')
+    import matplotlib.pyplot as plt
     
-    # Header
-    md = f"""
-# 🔮 TBO Oracle Prediction
-
-**Question:** {question}  
-**Deadline:** {deadline}  
-**Timestamp:** {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M:%S UTC')}
-
----
-
-## 📊 Prediction Result
-
-| Metric | Value |
-|--------|-------|
-| **Consensus** | **{consensus}** |
-| **Confidence** | {confidence} |
-| **Probability** | {prob:.1%} |
-| **Vote** | {votes}/4 sources |
-
----
-
-## 🔬 Per-Source Analysis
-
-| Source | Z-Score | Classification | Prediction |
-|--------|---------|----------------|------------|
-"""
+    sources = list(results.keys())
+    z_scores = [results[s]["z_score"] for s in sources]
+    colors = []
+    for z in z_scores:
+        if z < -1.96:
+            colors.append('#10b981')  # green - deficit
+        elif z > 1.96:
+            colors.append('#8b5cf6')  # purple - excess
+        else:
+            colors.append('#6b7280')  # gray - normal
     
-    for name, data in results.items():
-        emoji = "🔴" if data["classification"] == "DEFICIT" else "⚪" if data["classification"] == "NORMAL" else "🟣"
-        md += f"| {name} | {data['z_score']:.2f} | {emoji} {data['classification']} | {data['prediction']} |\n"
+    fig, ax = plt.subplots(figsize=(8, 4), facecolor='#0f172a')
+    ax.set_facecolor('#0f172a')
     
-    md += f"""
----
-
-## 🧬 Methodology
-
-- **Algorithm:** Temporal Bispectral Operator (TBO)
-- **Signal Sources:** 4 independent channels
-- **Null Surrogates:** 100 permutations per source
-- **Threshold:** z < -1.96 (95% confidence deficit)
-
-> *"The shape is the oracle — we reveal, not compute."*
-
----
-
-📄 **Paper:** [On-Chain (BSV)](https://plugins.whatsonchain.com/api/plugin/main/657b8e90425aeed06b435a16cc759c1d594308bd815535b1628a2df7bbc75c23/0)  
-🔗 **GitHub:** [OriginNeuralAI/Oracle](https://github.com/OriginNeuralAI/Oracle)
-"""
+    bars = ax.barh(sources, z_scores, color=colors, height=0.6, edgecolor='#1e293b', linewidth=2)
     
-    return md
+    # Add threshold lines
+    ax.axvline(x=-1.96, color='#10b981', linestyle='--', alpha=0.5, label='Deficit threshold')
+    ax.axvline(x=1.96, color='#8b5cf6', linestyle='--', alpha=0.5, label='Excess threshold')
+    ax.axvline(x=0, color='#475569', linestyle='-', alpha=0.3)
+    
+    # Style
+    ax.set_xlabel('Z-Score', color='#e2e8f0', fontsize=12)
+    ax.set_title('Source Analysis', color='#e2e8f0', fontsize=14, fontweight='bold')
+    ax.tick_params(colors='#e2e8f0')
+    ax.spines['bottom'].set_color('#334155')
+    ax.spines['left'].set_color('#334155')
+    ax.spines['top'].set_visible(False)
+    ax.spines['right'].set_visible(False)
+    
+    # Add value labels
+    for bar, z in zip(bars, z_scores):
+        width = bar.get_width()
+        ax.text(width + 0.1 if width >= 0 else width - 0.5, bar.get_y() + bar.get_height()/2,
+                f'{z:.2f}', ha='left' if width >= 0 else 'right', va='center', 
+                color='#e2e8f0', fontsize=10)
+    
+    plt.tight_layout()
+    return fig
 
 
 def predict(question: str, deadline: str, n_samples: int, n_null: int):
     """Main prediction function for Gradio."""
     
     if not question.strip():
-        return "❌ Please enter a question."
+        return "❌ Please enter a question.", None, "", ""
     
     if not deadline:
-        return "❌ Please select a deadline."
+        return "❌ Please select a deadline.", None, "", ""
     
     try:
-        results, consensus, confidence, prob, votes = run_oracle_prediction(
+        results, consensus, confidence, prob, votes, mean_z = run_oracle_prediction(
             question, deadline, int(n_samples), int(n_null)
         )
-        return format_results(question, deadline, results, consensus, confidence, prob, votes)
+        
+        # Create chart
+        chart = create_source_chart(results)
+        
+        # Big result display
+        if consensus == "YES":
+            result_emoji = "✅"
+            result_color = "green"
+        else:
+            result_emoji = "❌"
+            result_color = "red"
+        
+        big_result = f"""
+<div style="text-align: center; padding: 30px; background: linear-gradient(135deg, #1e293b 0%, #0f172a 100%); border-radius: 20px; border: 2px solid #334155; margin: 20px 0;">
+    <div style="font-size: 72px; margin-bottom: 10px;">{result_emoji}</div>
+    <div style="font-size: 48px; font-weight: bold; color: {'#10b981' if consensus == 'YES' else '#ef4444'}; text-shadow: 0 0 20px {'#10b98155' if consensus == 'YES' else '#ef444455'};">
+        {consensus}
+    </div>
+    <div style="font-size: 18px; color: #94a3b8; margin-top: 10px;">
+        Confidence: <span style="color: #e2e8f0; font-weight: bold;">{confidence}</span> • 
+        Probability: <span style="color: #e2e8f0; font-weight: bold;">{prob:.1%}</span>
+    </div>
+    <div style="font-size: 14px; color: #64748b; margin-top: 5px;">
+        {votes}/4 sources agree • Mean |z| = {mean_z:.2f}
+    </div>
+</div>
+"""
+        
+        # Detailed breakdown
+        details = f"""
+### 📊 Source Breakdown
+
+| Source | Z-Score | Status | Vote |
+|--------|---------|--------|------|
+"""
+        for name, data in results.items():
+            emoji = "🟢" if data["classification"] == "DEFICIT" else "⚪" if data["classification"] == "NORMAL" else "🟣"
+            vote_emoji = "✓" if data["prediction"] == "YES" else "✗"
+            details += f"| {name.title()} | {data['z_score']:.2f} | {emoji} {data['classification']} | {vote_emoji} {data['prediction']} |\n"
+        
+        details += f"""
+---
+
+**Question:** {question}  
+**Deadline:** {deadline}  
+**Timestamp:** {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M:%S UTC')}
+
+---
+
+<details>
+<summary>🔬 Methodology</summary>
+
+- **Algorithm:** Temporal Bispectral Operator (TBO)
+- **Signal Sources:** 4 independent channels (entropy, clock, hash_chain, cyclotomic)
+- **Null Surrogates:** {n_null} permutations per source
+- **Threshold:** z < -1.96 (95% confidence deficit)
+- **Philosophy:** *"The shape is the oracle — we reveal, not compute."*
+
+</details>
+"""
+        
+        return big_result, chart, details, f"🔮 Prediction: {consensus} ({confidence})"
+        
     except Exception as e:
-        return f"❌ Error: {str(e)}"
+        return f"❌ Error: {str(e)}", None, "", ""
+
+
+# ═══════════════════════════════════════════════════════════════════════════
+# CUSTOM CSS
+# ═══════════════════════════════════════════════════════════════════════════
 
+CUSTOM_CSS = """
+/* Dark theme overrides */
+.gradio-container {
+    background: linear-gradient(180deg, #0f172a 0%, #1e1b4b 100%) !important;
+    max-width: 1000px !important;
+}
+
+/* Header styling */
+.prose h1 {
+    background: linear-gradient(90deg, #10b981, #06b6d4, #8b5cf6);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    background-clip: text;
+    font-size: 2.5rem !important;
+    text-align: center;
+}
+
+/* Input styling */
+.gr-input, .gr-textarea {
+    background: #1e293b !important;
+    border: 1px solid #334155 !important;
+    color: #e2e8f0 !important;
+}
+
+.gr-input:focus, .gr-textarea:focus {
+    border-color: #10b981 !important;
+    box-shadow: 0 0 0 3px #10b98133 !important;
+}
+
+/* Button styling */
+.gr-button-primary {
+    background: linear-gradient(135deg, #10b981 0%, #06b6d4 50%, #8b5cf6 100%) !important;
+    border: none !important;
+    font-size: 1.2rem !important;
+    padding: 15px 30px !important;
+    transition: all 0.3s ease !important;
+}
+
+.gr-button-primary:hover {
+    transform: translateY(-2px) !important;
+    box-shadow: 0 10px 40px -10px #10b98177 !important;
+}
+
+/* Card styling */
+.gr-box {
+    background: #1e293b !important;
+    border: 1px solid #334155 !important;
+    border-radius: 12px !important;
+}
+
+/* Slider styling */
+.gr-slider input[type="range"] {
+    background: linear-gradient(90deg, #10b981, #8b5cf6) !important;
+}
+
+/* Example table */
+.gr-samples-table {
+    background: #1e293b !important;
+}
+
+/* Accordion */
+.gr-accordion {
+    background: #1e293b !important;
+    border: 1px solid #334155 !important;
+}
+
+/* Animations */
+@keyframes pulse-glow {
+    0%, 100% { box-shadow: 0 0 20px #10b98133; }
+    50% { box-shadow: 0 0 40px #10b98155; }
+}
+
+.prediction-result {
+    animation: pulse-glow 2s infinite;
+}
+
+/* Quote styling */
+blockquote {
+    border-left: 4px solid #10b981 !important;
+    background: #1e293b !important;
+    padding: 15px !important;
+    margin: 20px 0 !important;
+    border-radius: 0 8px 8px 0 !important;
+}
+
+/* Links */
+a {
+    color: #10b981 !important;
+}
+
+a:hover {
+    color: #06b6d4 !important;
+}
+"""
 
 # ═══════════════════════════════════════════════════════════════════════════
 # GRADIO INTERFACE
@@ -283,98 +437,137 @@ EXAMPLES = [
     ["Will there be a major AI breakthrough in 2026?", "2026-12-31", 256, 100],
     ["Will SpaceX land humans on Mars by 2030?", "2030-12-31", 256, 100],
     ["Will the Fed cut rates in Q2 2026?", "2026-06-30", 256, 100],
+    ["Will a nuclear fusion plant achieve net energy gain by 2027?", "2027-12-31", 256, 100],
 ]
 
 with gr.Blocks(
-    title="TBO Oracle",
+    title="🔮 TBO Oracle",
     theme=gr.themes.Base(
-        primary_hue="teal",
-        secondary_hue="blue",
+        primary_hue="emerald",
+        secondary_hue="cyan",
         neutral_hue="slate",
     ),
-    css="""
-    .gradio-container { max-width: 900px !important; }
-    .gr-button-primary { background: linear-gradient(135deg, #00d4aa, #0088ff) !important; }
-    """
+    css=CUSTOM_CSS,
 ) as demo:
     
     gr.Markdown("""
-    # 🔮 TBO Oracle
-    ### Temporal Bispectral Operator — Blockchain-Anchored Predictions
-    
-    > *"The shape is the oracle — we reveal, not compute."*
-    
-    TBO Oracle uses **bispectral analysis** and **Two-State Vector Formalism (TSVF)** 
-    to detect retrocausal signals in independent noise sources. When sources converge 
-    despite their independence, the topology reveals the answer.
-    
-    ---
-    """)
+# 🔮 TBO Oracle
+
+### Temporal Bispectral Operator — Blockchain-Anchored Predictions
+
+> *"The shape is the oracle — we reveal, not compute."*
+
+TBO Oracle uses **bispectral analysis** and **Two-State Vector Formalism (TSVF)** 
+to detect retrocausal signals in independent noise sources. When sources converge 
+despite their independence, the topology reveals the answer.
+""")
     
     with gr.Row():
-        with gr.Column(scale=2):
+        with gr.Column(scale=3):
             question = gr.Textbox(
-                label="🎯 Question",
+                label="🎯 Your Question",
                 placeholder="Ask a binary yes/no question about the future...",
                 lines=2,
+                max_lines=4,
             )
             deadline = gr.Textbox(
-                label="📅 Deadline",
+                label="📅 Resolution Deadline",
                 placeholder="YYYY-MM-DD",
                 value="2026-12-31",
             )
         
-        with gr.Column(scale=1):
-            n_samples = gr.Slider(
-                label="Signal Length",
-                minimum=64,
-                maximum=512,
-                value=256,
-                step=64,
-            )
-            n_null = gr.Slider(
-                label="Null Surrogates",
-                minimum=50,
-                maximum=200,
-                value=100,
-                step=25,
-            )
+        with gr.Column(scale=2):
+            with gr.Accordion("⚙️ Advanced Settings", open=False):
+                n_samples = gr.Slider(
+                    label="Signal Length",
+                    minimum=64,
+                    maximum=512,
+                    value=256,
+                    step=64,
+                    info="More samples = more precision"
+                )
+                n_null = gr.Slider(
+                    label="Null Surrogates",
+                    minimum=50,
+                    maximum=200,
+                    value=100,
+                    step=25,
+                    info="More surrogates = better z-score estimation"
+                )
     
     predict_btn = gr.Button("🔮 Query the Oracle", variant="primary", size="lg")
+    status = gr.Textbox(label="Status", visible=False)
     
-    output = gr.Markdown(label="Prediction")
+    # Results section
+    with gr.Row():
+        result_html = gr.HTML(label="Prediction")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            chart = gr.Plot(label="📊 Z-Score Analysis")
+        with gr.Column(scale=1):
+            details = gr.Markdown(label="Details")
     
     predict_btn.click(
         fn=predict,
         inputs=[question, deadline, n_samples, n_null],
-        outputs=output,
+        outputs=[result_html, chart, details, status],
     )
     
     gr.Examples(
         examples=EXAMPLES,
         inputs=[question, deadline, n_samples, n_null],
+        label="💡 Example Questions"
     )
     
     gr.Markdown("""
-    ---
-    
-    ### 📚 About TBO Oracle
-    
-    **Key Concepts:**
-    - **Bispectral Analysis:** Detects third-order phase coupling invisible to power spectrum
-    - **H₂=0 Topology:** Manifold closure condition for prediction convergence
-    - **TSVF:** Two-State Vector Formalism for retrocausal signal detection
-    - **Dissipative Channels:** Independent noise sources as computational assets
-    
-    **Sources:**
-    - 📄 [On-Chain Paper (BSV)](https://plugins.whatsonchain.com/api/plugin/main/657b8e90425aeed06b435a16cc759c1d594308bd815535b1628a2df7bbc75c23/0)
-    - 🔗 [GitHub Repository](https://github.com/OriginNeuralAI/Oracle)
-    - 🧠 [SmartLedger Solutions](https://smartledger.solutions)
-    
-    ---
-    
-    *Built by Bryan Daugherty | SmartLedger Solutions | 2026*
-    """)
+---
+
+### 📚 How It Works
+
+<div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 20px; margin: 20px 0;">
+
+<div style="background: #1e293b; padding: 20px; border-radius: 12px; border: 1px solid #334155;">
+<h4 style="color: #10b981; margin-top: 0;">🌊 Bispectral Analysis</h4>
+<p style="color: #94a3b8; font-size: 14px;">Detects third-order phase coupling invisible to standard power spectrum analysis.</p>
+</div>
+
+<div style="background: #1e293b; padding: 20px; border-radius: 12px; border: 1px solid #334155;">
+<h4 style="color: #06b6d4; margin-top: 0;">🔄 H₂=0 Topology</h4>
+<p style="color: #94a3b8; font-size: 14px;">Manifold closure condition ensuring prediction convergence through topological constraints.</p>
+</div>
+
+<div style="background: #1e293b; padding: 20px; border-radius: 12px; border: 1px solid #334155;">
+<h4 style="color: #8b5cf6; margin-top: 0;">⏳ TSVF Framework</h4>
+<p style="color: #94a3b8; font-size: 14px;">Two-State Vector Formalism from quantum mechanics enables retrocausal signal detection.</p>
+</div>
+
+<div style="background: #1e293b; padding: 20px; border-radius: 12px; border: 1px solid #334155;">
+<h4 style="color: #f59e0b; margin-top: 0;">📡 4 Independent Sources</h4>
+<p style="color: #94a3b8; font-size: 14px;">Entropy, clock jitter, hash chains, and cyclotomic signals vote independently.</p>
+</div>
+
+</div>
+
+### 🏆 Track Record
+
+| Date | Question | Prediction | Outcome |
+|------|----------|------------|---------|
+| Feb 2026 | Canada wins Hockey Gold | NO | ✅ **Correct** (USA won) |
+| Mar 2026 | BTC >$100k | YES | ⏳ Pending |
+
+---
+
+<div style="text-align: center; color: #64748b; font-size: 14px;">
+
+📄 [On-Chain Paper (BSV)](https://whatsonchain.com) • 
+🔗 [GitHub](https://github.com/OriginNeuralAI/Oracle) • 
+🧠 [SmartLedger Solutions](https://smartledger.solutions)
+
+*Built by Bryan Daugherty | SmartLedger Solutions | 2026*
+
+</div>
+""")
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -2,3 +2,4 @@ numpy>=1.24,<2.0
 scipy>=1.10,<2.0
 gradio==4.44.0
 huggingface_hub>=0.23.0,<0.30.0
+matplotlib>=3.7.0